© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    dates and times followed by various sequences of numbers

    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
    447
    +0.22
    0.8%
    198
    +0.15
    0.5%
    159
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.22
    0.05
    326
    +0.15
    0.08
    731
    +0.12
    0.04
    Negative Logits
    ilda
    -0.99
    chev
    -0.99
    lov
    -0.97
    romeda
    -0.91
    rolet
    -0.86
    DERR
    -0.86
    UGE
    -0.84
    yip
    -0.82
    resa
    -0.81
    gue
    -0.80
    POSITIVE LOGITS
    IJ
    0.85
    ŀ
    0.81
    ĸļ
    0.81
    Ģ
    0.78
     Radar
    0.77
     Resort
    0.72
     Miscellaneous
    0.72
     Debug
    0.72
    ķ
    0.71
     Tribal
    0.71
    Activations Density 0.940%

    No Known Activations