© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 138
    Prev
    Next
    INDEX
    Explanations

    terms related to news articles, press releases, and photographs depicting various incidents and events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "file" and "photo" related to journalistic or documentation contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    583
    +0.12
    0.5%
    455
    +0.12
    0.5%
    540
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.08
    113
    +0.12
    0.04
    683
    +0.12
    0.04
    Negative Logits
    orically
    -0.87
    angular
    -0.86
    quickShipAvailable
    -0.85
    orical
    -0.84
     ende
    -0.83
    osp
    -0.81
    owered
    -0.79
    agne
    -0.79
    mal
    -0.79
     GSL
    -0.78
    POSITIVE LOGITS
    20439
    1.01
     caption
    0.87
    mates
    0.85
    buster
    0.83
    ters
    0.83
    Upload
    0.82
    mma
    0.81
    backs
    0.81
    hart
    0.80
    ystem
    0.80
    Activations Density 0.905%

    No Known Activations