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 768
    5. 8-RES_FS768-JB
    6. 266
    Prev
    Next
    INDEX
    Explanations

    information related to political and social issues, including crime statistics and legislative updates

    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
    241
    +0.13
    0.6%
    314
    +0.12
    0.5%
    546
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.13
    0.14
    363
    +0.12
    0.10
    393
    +0.11
    0.17
    Negative Logits
    utenberg
    -0.75
     swe
    -0.69
     transformations
    -0.67
     sugg
    -0.65
     cipher
    -0.65
     horm
    -0.64
     descriptor
    -0.64
     endings
    -0.63
     tricks
    -0.63
     reversible
    -0.63
    POSITIVE LOGITS
    England
    1.16
     Northern
    1.10
     Guam
    1.10
    Northern
    1.09
    Mexico
    1.08
     Southeast
    1.03
     Chile
    1.02
     Taiwan
    1.00
     Papua
    1.00
     South
    1.00
    Activations Density 5.265%

    No Known Activations