© 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. 40004
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific animated series and characters within it

    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
    128
    +0.08
    0.5%
    269
    +0.07
    0.5%
    447
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.08
    0.11
    326
    +0.07
    0.23
    659
    +0.07
    0.11
    Negative Logits
    iculty
    -0.55
    UTE
    -0.50
     commissioners
    -0.43
     Commissioners
    -0.42
     commissioner
    -0.41
     postage
    -0.40
    judicial
    -0.40
     dow
    -0.39
    ORD
    -0.39
     whip
    -0.39
    POSITIVE LOGITS
    nen
    0.62
    halla
    0.59
    lio
    0.59
     Frieza
    0.59
    roots
    0.55
    \\\\\\\\
    0.54
     Gohan
    0.54
    colo
    0.53
     Saiyan
    0.53
    kowski
    0.52
    Activations Density 9.081%

    No Known Activations