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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 905
    Prev
    Next
    INDEX
    Explanations

    references to movie reviews or critiques

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    404
    +0.11
    0.5%
    169
    +0.10
    0.5%
    159
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.07
    284
    +0.10
    0.11
    232
    +0.10
    0.10
    Negative Logits
    abase
    -0.82
    SPONSORED
    -0.77
    href
    -0.70
    ortium
    -0.65
    mpeg
    -0.64
    natureconservancy
    -0.63
    lehem
    -0.61
    acca
    -0.61
    sole
    -0.60
    ersen
    -0.58
    POSITIVE LOGITS
    kefeller
    0.85
     Janeiro
    0.78
     CTR
    0.72
    backer
    0.71
    restling
    0.66
    Berry
    0.60
     Grac
    0.60
    runner
    0.60
    monary
    0.60
    warts
    0.59
    Activations Density 3.116%

    No Known Activations