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 49152
    5. 8-RES_FS49152-JB
    6. 12141
    Prev
    Next
    INDEX
    Explanations

    terms associated with hardship or difficult circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.17
    0.8%
    481
    +0.12
    0.6%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.01
    34
    +0.12
    0.01
    291
    +0.11
    0.01
    Negative Logits
    glomer
    -0.70
    tein
    -0.69
    zyme
    -0.66
     logos
    -0.66
     Prediction
    -0.62
    ombs
    -0.62
     nucle
    -0.62
     weights
    -0.61
     confir
    -0.61
     certific
    -0.59
    POSITIVE LOGITS
     plight
    1.06
    ously
    0.94
    retched
    0.78
     plag
    0.77
    ingly
    0.73
    oire
    0.73
    dden
    0.72
    ours
    0.71
    pid
    0.68
    iful
    0.67
    Activations Density 0.022%

    No Known Activations