© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33172
    Prev
    Next
    INDEX
    Explanations

    code syntax errors

    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
    132
    +0.11
    0.6%
    556
    +0.09
    0.5%
    447
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.11
    0.07
    556
    +0.09
    0.08
    661
    +0.08
    0.04
    Negative Logits
    ¥µ
    -0.66
    endars
    -0.53
    ATURES
    -0.52
    osate
    -0.52
    zos
    -0.51
    PDATE
    -0.51
     experien
    -0.51
    »Ĵ
    -0.51
    Ń·
    -0.50
    skirts
    -0.50
    POSITIVE LOGITS
    ))
    0.63
     ||
    0.59
     );
    0.57
     sidx
    0.56
    &&
    0.55
    );
    0.55
    ################
    0.53
    +(
    0.52
    }{
    0.52
     Malfoy
    0.52
    Activations Density 7.696%

    No Known Activations