© 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. 33035
    Prev
    Next
    INDEX
    Explanations

    phrases indicating demands, requests, and calls to action

    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
    +0.27
    1.4%
    393
    +0.18
    0.9%
    679
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.27
    0.24
    393
    +0.18
    0.26
    255
    +0.13
    0.14
    Negative Logits
    ãĤ§
    -0.63
    ãĥ¬
    -0.62
    ãĤ´ãĥ³
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
    ãĤ¨ãĥ«
    -0.59
    rss
    -0.59
    TAG
    -0.59
    ãĥ¼ãĤ¯
    -0.58
    Ö
    -0.58
    ãĥ¡
    -0.56
    POSITIVE LOGITS
    soever
    0.83
     users
    0.68
     accompany
    0.65
     electors
    0.64
     motorists
    0.64
     policymakers
    0.63
     programmers
    0.63
     everyone
    0.62
    chers
    0.62
     recipients
    0.60
    Activations Density 11.318%

    No Known Activations