© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting up or establishing something

    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
    270
    +0.18
    0.6%
    125
    +0.17
    0.6%
    314
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.18
    0.05
    270
    +0.17
    0.03
    717
    +0.16
    0.03
    Negative Logits
    obi
    -1.08
    onso
    -1.02
    annah
    -1.02
    Brow
    -0.94
    orie
    -0.92
    ory
    -0.88
    "],"
    -0.86
    hound
    -0.86
    iveness
    -0.86
    catentry
    -0.85
    POSITIVE LOGITS
     tents
    1.22
    dates
    1.14
    olicy
    1.14
    river
    1.08
     shop
    1.03
    dule
    0.98
    dating
    0.97
     camp
    0.95
    eering
    0.94
     rapport
    0.93
    Activations Density 0.593%

    No Known Activations