Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13576
    Prev
    Next
    INDEX
    Explanations

    references to stun guns

    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
    276
    +0.11
    0.6%
    497
    +0.10
    0.6%
    15
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.25
    326
    +0.10
    0.24
    709
    +0.09
    0.12
    Negative Logits
     âĶľ
    -0.67
    ãĤ¶
    -0.64
    vernment
    -0.62
    eworks
    -0.62
    aternity
    -0.62
    natureconservancy
    -0.60
    ullivan
    -0.60
    ucc
    -0.60
    ername
    -0.59
     sshd
    -0.59
    POSITIVE LOGITS
    ting
    0.98
    ted
    0.88
    ned
    0.80
    ning
    0.78
    ishment
    0.77
    eful
    0.73
    ner
    0.71
    ners
    0.71
    ray
    0.69
    ingly
    0.69
    Activations Density 8.840%

    No Known Activations