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 3072
    5. 8-RES_FS3072-JB
    6. 2762
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month Day, Year (e.g., March 26, 2017)

    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
    194
    +0.09
    0.4%
    472
    +0.09
    0.4%
    373
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.09
    0.07
    6
    +0.09
    0.07
    194
    +0.08
    0.06
    Negative Logits
    keley
    -0.71
    paio
    -0.67
    aceae
    -0.63
    indal
    -0.59
     equilibrium
    -0.58
    cases
    -0.57
    phia
    -0.56
    ModLoader
    -0.55
     Laboratory
    -0.55
     computers
    -0.55
    POSITIVE LOGITS
    advertising
    0.78
    utm
    0.76
    à¼
    0.72
     Ùħ
    0.69
    )</
    0.68
    Loading
    0.68
    ð
    0.67
     VIDEOS
    0.67
    Ñı
    0.67
    Reply
    0.67
    Activations Density 0.509%

    No Known Activations