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. 259
    Prev
    Next
    INDEX
    Explanations

    information related to definitions and explanations

    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
    430
    +0.14
    0.7%
    679
    +0.11
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.14
    0.12
    757
    +0.11
    0.10
    551
    +0.11
    0.12
    Negative Logits
     VIDEOS
    -0.76
    MENTS
    -0.66
    Bas
    -0.65
    athi
    -0.63
     Anything
    -0.60
    GY
    -0.60
    STE
    -0.59
    DI
    -0.59
    MENT
    -0.58
    BOX
    -0.58
    POSITIVE LOGITS
     incidentally
    1.07
     specializes
    1.02
     comprises
    1.02
     oversees
    1.01
     operates
    0.96
     consists
    0.96
     translates
    0.94
     oversaw
    0.92
     governs
    0.92
     represents
    0.91
    Activations Density 1.817%

    No Known Activations