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 49152
    5. 8-RES_FS49152-JB
    6. 23917
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.13
    0.6%
    537
    +0.11
    0.5%
    427
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.04
    427
    +0.11
    0.03
    716
    +0.11
    0.03
    Negative Logits
     Edited
    -0.65
    rers
    -0.61
     cir
    -0.59
    sson
    -0.59
     unpre
    -0.59
     EntityItem
    -0.58
     Cullen
    -0.58
     moder
    -0.58
     temper
    -0.57
     mastering
    -0.56
    POSITIVE LOGITS
    shaped
    1.21
    bomb
    0.98
    Day
    0.93
    plus
    0.92
    level
    0.90
    series
    0.89
    dimensional
    0.89
    word
    0.88
    minus
    0.88
    G
    0.86
    Activations Density 0.024%

    No Known Activations