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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2044
    Prev
    Next
    INDEX
    Explanations

    statements describing current situations or circumstances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    756
    +0.11
    0.5%
    642
    +0.10
    0.5%
    739
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.09
    575
    +0.10
    0.09
    288
    +0.10
    0.09
    Negative Logits
    ipedia
    -0.83
    yright
    -0.80
    cott
    -0.79
    tool
    -0.79
    ithe
    -0.78
    tein
    -0.78
    enic
    -0.77
    sonian
    -0.74
    cot
    -0.72
    thood
    -0.72
    POSITIVE LOGITS
     conducive
    0.99
     quo
    0.95
     unfolding
    0.95
     circumstances
    0.93
     conditions
    0.92
     Situation
    0.91
     situations
    0.87
     worsened
    0.87
     unfolded
    0.86
     Conditions
    0.84
    Activations Density 1.157%

    No Known Activations