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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45045
    Prev
    Next
    INDEX
    Explanations

    information related to legal matters, political events, and sport events

    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
    167
    +0.13
    0.6%
    26
    +0.11
    0.5%
    742
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.20
    352
    +0.11
    0.16
    742
    +0.11
    0.13
    Negative Logits
    ricular
    -0.74
    forcing
    -0.66
    nces
    -0.65
    imaru
    -0.64
    ãĥĦ
    -0.63
     Normandy
    -0.63
    lished
    -0.62
    ãĥ¼ãĥ«
    -0.62
    ãĥĹ
    -0.61
    =-=-=-=-=-=-=-=-
    -0.61
    POSITIVE LOGITS
    anguage
    0.87
    arge
    0.85
    endon
    0.84
    aughter
    0.83
    DN
    0.78
    ibrary
    0.77
    ibraries
    0.77
    yrics
    0.76
    iquid
    0.75
    TON
    0.74
    Activations Density 7.036%

    No Known Activations