Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45569
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency or immediate attention

    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
    356
    +0.10
    0.6%
    755
    +0.07
    0.5%
    725
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.10
    0.11
    713
    +0.07
    0.05
    635
    +0.07
    0.08
    Negative Logits
    elson
    -0.59
    ramid
    -0.56
    wagen
    -0.55
    owitz
    -0.54
    vik
    -0.52
    Ń·
    -0.49
    rug
    -0.48
    aine
    -0.48
    bowl
    -0.47
    aden
    -0.47
    POSITIVE LOGITS
     urgency
    0.80
     urgent
    0.75
     urgently
    0.66
     concern
    0.58
     overdue
    0.57
     notifications
    0.57
     danger
    0.57
     proble
    0.54
     imperative
    0.52
     threat
    0.52
    Activations Density 11.231%

    No Known Activations