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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21473
    Prev
    Next
    INDEX
    Explanations

    script code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    160
    +0.12
    0.5%
    346
    +0.11
    0.5%
    741
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.02
    456
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
    atform
    -0.80
     Manson
    -0.68
     Divide
    -0.66
     Pearce
    -0.63
     screenings
    -0.63
     Dynamics
    -0.62
     Stead
    -0.61
     Participation
    -0.61
     Vide
    -0.61
    ulhu
    -0.60
    POSITIVE LOGITS
    taboola
    1.12
    blank
    1.04
    main
    0.92
    webkit
    0.92
    tra
    0.89
    chance
    0.88
    nom
    0.87
    self
    0.87
    default
    0.86
    canon
    0.86
    Activations Density 0.017%

    No Known Activations