© 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
    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. 13731
    Prev
    Next
    INDEX
    Explanations

    instances of actions or situations related to sleeping

    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
    48
    +0.12
    0.6%
    420
    +0.09
    0.5%
    447
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.12
    0.08
    554
    +0.09
    -0.11
    125
    +0.09
    0.07
    Negative Logits
    ific
    -0.83
    İ
    -0.75
    icity
    -0.70
    icals
    -0.69
    adelphia
    -0.65
    cean
    -0.63
    auga
    -0.63
    icon
    -0.63
    iferation
    -0.62
    ala
    -0.61
    POSITIVE LOGITS
     quarters
    0.71
     Beaut
    0.69
     sleeps
    0.68
     pill
    0.68
     Rooms
    0.64
     sleeping
    0.63
     awake
    0.63
     sleeper
    0.62
     rooms
    0.62
     indoors
    0.62
    Activations Density 9.517%

    No Known Activations