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

    Neuronpedia

    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. 5907
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical instructions or formatting

    oai_token-act-pair · gpt-3.5-turbo
    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
    393
    +0.28
    1.1%
    318
    +0.13
    0.5%
    717
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.28
    0.09
    393
    +0.13
    0.10
    385
    +0.12
    0.08
    Negative Logits
    arthed
    -0.83
    boxing
    -0.80
    atchewan
    -0.78
    stad
    -0.77
    ]'
    -0.77
    inois
    -0.75
     Baghd
    -0.75
    ichick
    -0.74
    warts
    -0.72
    ancock
    -0.72
    POSITIVE LOGITS
     hashtag
    1.03
     levers
    1.03
     newfound
    1.02
     brakes
    0.98
     borrowed
    0.94
     proverbial
    0.91
     same
    0.89
     usual
    0.88
     scarce
    0.87
     customary
    0.86
    Activations Density 1.588%

    No Known Activations