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. 191
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling or fictional events

    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
    393
    +0.28
    1.4%
    362
    +0.24
    1.2%
    385
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.28
    0.44
    393
    +0.24
    0.30
    608
    +0.15
    0.34
    Negative Logits
     namely
    -0.86
     besides
    -0.78
    thood
    -0.76
     whenever
    -0.76
     according
    -0.75
     because
    -0.74
     suppose
    -0.74
     without
    -0.74
     with
    -0.74
     wherein
    -0.73
    POSITIVE LOGITS
     same
    1.47
     latter
    1.44
     slightest
    1.42
     entirety
    1.39
     aforementioned
    1.36
     remainder
    1.34
     entire
    1.33
     smallest
    1.25
    ses
    1.25
     widest
    1.17
    Activations Density 4.021%

    No Known Activations