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. 190
    Prev
    Next
    INDEX
    Explanations

    references to real estate development and community projects

    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
    420
    +0.11
    0.5%
    481
    +0.11
    0.5%
    596
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.11
    0.10
    270
    +0.11
    0.06
    325
    +0.10
    0.12
    Negative Logits
    obin
    -0.90
    sense
    -0.76
    brain
    -0.75
    verbal
    -0.75
    analy
    -0.74
     epigen
    -0.73
     memes
    -0.73
    intent
    -0.73
     impuls
    -0.73
    gey
    -0.72
    POSITIVE LOGITS
     adjoining
    1.45
     downtown
    1.39
     buildings
    1.38
     adjacent
    1.36
     residences
    1.31
     residential
    1.31
     Located
    1.30
    Located
    1.29
     renovation
    1.29
     landsc
    1.28
    Activations Density 8.346%

    No Known Activations