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 24576
    5. 8-RES_FS24576-JB
    6. 23438
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    480
    +0.18
    0.8%
    447
    +0.14
    0.6%
    71
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    523
    +0.18
    0.04
    31
    +0.14
    0.04
    310
    +0.13
    0.04
    Negative Logits
     administr
    -0.92
    undai
    -0.76
     newsp
    -0.71
     arrang
    -0.69
     pse
    -0.68
    mble
    -0.68
     manifold
    -0.67
     challeng
    -0.67
     federation
    -0.67
     manif
    -0.65
    POSITIVE LOGITS
     ILCS
    1.20
     SHARES
    1.05
    80
    0.96
    70
    0.92
    00
    0.88
    804
    0.86
    765
    0.86
    803
    0.85
    301
    0.85
    è£ħ
    0.85
    Activations Density 0.094%

    No Known Activations