© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34738
    Prev
    Next
    INDEX
    Explanations

    text related to political and social activism, specifically focusing on community action and causes

    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
    665
    +0.12
    0.6%
    393
    +0.12
    0.6%
    314
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.21
    22
    +0.12
    0.17
    362
    +0.09
    0.17
    Negative Logits
     convol
    -0.62
     unemploy
    -0.58
     bye
    -0.55
     entrants
    -0.54
     Illustrated
    -0.54
     Logged
    -0.53
     impro
    -0.53
     millennials
    -0.53
    +)
    -0.52
     pegged
    -0.51
    POSITIVE LOGITS
     lieu
    0.95
     vain
    0.91
     regards
    0.88
    escap
    0.88
     accordance
    0.87
    ordinate
    0.85
    offensive
    0.84
     terms
    0.83
    animate
    0.83
    breeding
    0.83
    Activations Density 6.860%

    No Known Activations