© 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 EvalsExportsinterp-engineNEWAPI 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. 32109
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and software development, specifically focusing on actions like compiling, downloading source code, and running setup files

    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
    93
    +0.05
    0.5%
    666
    +0.05
    0.5%
    214
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.05
    0.17
    288
    +0.05
    0.17
    526
    +0.04
    -0.04
    Negative Logits
    ivia
    -0.39
    elsius
    -0.37
    yson
    -0.35
    ļéĨĴ
    -0.35
    ively
    -0.35
    ayette
    -0.34
    airs
    -0.34
    ensive
    -0.34
    opia
    -0.33
    enza
    -0.33
    POSITIVE LOGITS
     tar
    0.43
    LEASE
    0.33
     extracted
    0.30
    bourg
    0.30
    ZI
    0.29
     Kong
    0.29
    dated
    0.29
     dd
    0.29
    tar
    0.28
    \\\\
    0.28
    Activations Density 4.951%

    No Known Activations