© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13873
    Prev
    Next
    INDEX
    Explanations

    actions or attitudes related to shrugging (physically or metaphorically dismissing or being indifferent to something)

    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
    35
    +0.14
    0.7%
    285
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.22
    195
    +0.11
    0.00
    35
    +0.11
    0.07
    Negative Logits
    ciating
    -0.73
    wives
    -0.71
    cycl
    -0.67
    jas
    -0.66
    trump
    -0.65
    facts
    -0.64
    friends
    -0.64
    LET
    -0.62
    leon
    -0.61
    ãĥ´
    -0.61
    POSITIVE LOGITS
     shrug
    0.99
    acket
    0.79
     bye
    0.74
    Ö¼
    0.72
     shoulders
    0.70
     rub
    0.69
     aloud
    0.66
     awkwardly
    0.66
     bash
    0.65
    kowski
    0.64
    Activations Density 7.898%

    No Known Activations