Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 1311
    Prev
    Next
    INDEX
    Explanations

    quotes from interviews or statements

    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
    430
    +0.14
    0.7%
    426
    +0.10
    0.5%
    333
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.09
    426
    +0.10
    0.08
    333
    +0.10
    0.07
    Negative Logits
    etheless
    -1.03
    ingu
    -0.77
    £ı
    -0.72
    »Ĵ
    -0.68
    bably
    -0.65
    anuts
    -0.65
    ¬¼
    -0.65
    successfully
    -0.64
    enfranch
    -0.63
    ĵĺ
    -0.63
    POSITIVE LOGITS
     said
    1.21
    said
    1.21
     says
    1.16
     reads
    1.16
     wrote
    1.07
     commented
    1.00
     joked
    0.98
     exclaimed
    0.98
     recalls
    0.97
     replied
    0.96
    Activations Density 0.682%

    No Known Activations