© 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. 12689
    Prev
    Next
    INDEX
    Explanations

    various software and entertainment titles

    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
    640
    +0.48
    2.4%
    160
    +0.11
    0.5%
    706
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.48
    0.23
    160
    +0.11
    0.14
    143
    +0.10
    0.09
    Negative Logits
    hement
    -0.89
    ername
    -0.82
    ktop
    -0.74
    arah
    -0.70
     McMaster
    -0.70
     Scion
    -0.69
    uly
    -0.69
    paio
    -0.69
    atos
    -0.68
    ings
    -0.65
    POSITIVE LOGITS
    âĵĺ
    0.97
    ?????-
    0.86
    ================================================================
    0.77
    effects
    0.77
    ----------------------------------------------------------------
    0.70
    Trivia
    0.70
    --------------------
    0.69
    ?????-?????-
    0.69
    Beta
    0.69
    FIN
    0.69
    Activations Density 1.239%

    No Known Activations