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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31904
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to emergency incidents and calls for help, especially involving 911

    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
    +0.17
    1.0%
    326
    +0.11
    0.6%
    709
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    550
    +0.17
    0.09
    326
    +0.11
    0.22
    639
    +0.09
    0.09
    Negative Logits
    wikipedia
    -0.72
    laus
    -0.63
    secut
    -0.62
    ju
    -0.60
    glomer
    -0.59
    rug
    -0.59
    xtap
    -0.58
    hend
    -0.57
    chin
    -0.57
    jong
    -0.57
    POSITIVE LOGITS
     911
    0.91
     dispatcher
    0.87
     caller
    0.67
     emergencies
    0.64
    gencies
    0.64
     hotline
    0.64
     announcer
    0.61
     calls
    0.60
     responders
    0.59
     transmitter
    0.58
    Activations Density 8.580%

    No Known Activations