© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    militias and armed groups in various geopolitical contexts

    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
    +0.14
    1.3%
    288
    +0.07
    0.7%
    496
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.20
    294
    +0.07
    0.04
    709
    +0.06
    0.10
    Negative Logits
    paren
    -0.36
    fixed
    -0.34
    âĸ¬
    -0.34
    lined
    -0.33
     Prediction
    -0.33
     Spiral
    -0.33
    terior
    -0.33
    cond
    -0.32
    ospital
    -0.32
    graph
    -0.32
    POSITIVE LOGITS
     militia
    0.50
     militias
    0.49
    llan
    0.44
     Militia
    0.40
     obliged
    0.38
    orsi
    0.38
    ments
    0.38
     brig
    0.38
    imore
    0.37
     members
    0.36
    Activations Density 7.404%

    No Known Activations