© 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. 40444
    Prev
    Next
    INDEX
    Explanations

    products and substances related to personal care and hygiene

    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
    +0.07
    0.8%
    288
    +0.06
    0.6%
    289
    +0.05
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.19
    326
    +0.06
    0.18
    50
    +0.05
    0.09
    Negative Logits
    umbered
    -0.31
    theless
    -0.29
    trl
    -0.29
    IGH
    -0.28
    ascade
    -0.28
    etermined
    -0.28
    HAM
    -0.28
    aughter
    -0.27
    CLASSIFIED
    -0.27
    CVE
    -0.27
    POSITIVE LOGITS
     opera
    0.47
     oper
    0.46
    pering
    0.39
    eless
    0.39
     soap
    0.36
    bub
    0.34
    mins
    0.33
    wich
    0.33
    boxing
    0.33
    pered
    0.33
    Activations Density 5.629%

    No Known Activations