© 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 Local
    9. 6-RES_SCL-AJT
    11. 34906
    Prev
    Next
    INDEX
    Explanations

    programming code structures like arrays, variable assignments, and mathematical updates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.16
    0.6%
    508
    +0.13
    0.5%
    337
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.36
    442
    +0.13
    0.11
    6
    +0.13
    0.20
    Negative Logits
    querque
    -0.98
    ãĥ¼ãĥĨ
    -0.93
    ibrary
    -0.85
    ģĸ
    -0.84
    INAL
    -0.83
    govtrack
    -0.80
    ļé
    -0.78
    ģ«
    -0.77
    ICAN
    -0.77
    ãĥĥãĥī
    -0.74
    POSITIVE LOGITS
    nesday
    1.08
    ÅĤ
    0.82
    anders
    0.80
     Tanzania
    0.78
     Norton
    0.75
    lich
    0.73
     poles
    0.72
    tel
    0.72
    ingen
    0.71
    eret
    0.71
    Activations Density 23.809%

    No Known Activations