© 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. 34698
    Prev
    Next
    INDEX
    Explanations

    references in academic texts

    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
    +0.25
    1.1%
    640
    +0.17
    0.7%
    758
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.42
    393
    +0.17
    0.35
    64
    +0.11
    -0.28
    Negative Logits
     thrott
    -0.62
    estate
    -0.61
    vered
    -0.61
     chops
    -0.61
    arers
    -0.60
    roph
    -0.59
    split
    -0.59
    orate
    -0.59
    ties
    -0.58
    Ń·
    -0.58
    POSITIVE LOGITS
    pmwiki
    0.96
    ibliography
    0.95
    Sources
    0.90
    BOOK
    0.87
    âĨij
    0.86
    agascar
    0.85
    sites
    0.81
     Encyclopedia
    0.78
    Books
    0.77
     Sources
    0.76
    Activations Density 16.297%

    No Known Activations