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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 147
    Prev
    Next
    INDEX
    Explanations

    information related to sports free agency

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    202
    +0.09
    0.4%
    602
    +0.09
    0.4%
    86
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.09
    0.09
    603
    +0.09
    0.10
    86
    +0.08
    0.10
    Negative Logits
     Feminist
    -0.92
     ®
    -0.77
    sylv
    -0.76
    sth
    -0.74
     UNESCO
    -0.73
     Governments
    -0.71
     OPER
    -0.69
     feminist
    -0.68
     umb
    -0.68
     Quartz
    -0.66
    POSITIVE LOGITS
     rookie
    1.56
     offseason
    1.51
     Rookie
    1.50
     undrafted
    1.44
    Coach
    1.44
     preseason
    1.42
     quarterback
    1.41
     teammate
    1.40
     linebacker
    1.39
     rookies
    1.36
    Activations Density 7.011%

    No Known Activations