© 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. 33056
    Prev
    Next
    INDEX
    Explanations

    words related to receiving authorization or consent for certain actions or decisions

    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
    679
    +0.14
    0.7%
    288
    +0.12
    0.6%
    447
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.18
    744
    +0.12
    0.11
    51
    +0.11
    0.10
    Negative Logits
    hed
    -0.75
    gm
    -0.72
     Canaver
    -0.69
    esthetic
    -0.65
     Lerner
    -0.64
    resp
    -0.64
     Penal
    -0.63
    hing
    -0.63
    nov
    -0.62
    hester
    -0.61
    POSITIVE LOGITS
     rating
    0.78
    worthiness
    0.75
    worthy
    0.74
     ratings
    0.70
     process
    0.70
     package
    0.69
     hearings
    0.65
    aneers
    0.64
     Rating
    0.64
     acceptance
    0.62
    Activations Density 4.196%

    No Known Activations