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 1536
    5. 8-RES_FS1536-JB
    6. 1284
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating timeframes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.11
    0.5%
    471
    +0.11
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.11
    0.13
    223
    +0.11
    0.11
    693
    +0.10
    0.12
    Negative Logits
    ettings
    -0.73
    achi
    -0.65
     inherit
    -0.62
    unct
    -0.62
    venge
    -0.60
    abol
    -0.60
    ques
    -0.58
    uana
    -0.57
    rophe
    -0.57
    iqu
    -0.56
    POSITIVE LOGITS
    Hz
    1.18
    %"
    1.17
    %
    1.14
    hz
    1.11
    %-
    1.05
     percent
    1.03
    Percent
    1.00
    %.
    0.98
    +)
    0.96
    percent
    0.95
    Activations Density 1.281%

    No Known Activations