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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13218
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, especially names of political figures and policymakers

    oai_token-act-pair · gpt-3.5-turbo

    names of people, specifically focusing on first or last names

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    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
    1
    +0.10
    0.6%
    623
    +0.09
    0.5%
    31
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    326
    +0.09
    0.21
    354
    +0.09
    0.09
    Negative Logits
    eem
    -0.69
    ħĭ
    -0.69
    conservancy
    -0.69
    lease
    -0.68
    yip
    -0.64
    ork
    -0.63
    BLE
    -0.59
    hov
    -0.59
    reen
    -0.57
    rame
    -0.56
    POSITIVE LOGITS
    icity
    0.77
    ians
    0.67
    ified
    0.63
    ivated
    0.58
    itude
    0.57
    IFIED
    0.56
    iola
    0.56
    uated
    0.56
    ican
    0.56
    ipe
    0.56
    Activations Density 6.433%

    No Known Activations