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. 23565
    Prev
    Next
    INDEX
    Explanations

    references to user-generated content and related user input

    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
    314
    +0.14
    0.6%
    124
    +0.12
    0.5%
    610
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.14
    0.04
    152
    +0.12
    0.04
    314
    +0.12
    0.01
    Negative Logits
    ulhu
    -0.71
     Slim
    -0.71
     knots
    -0.67
     Ital
    -0.65
     Jackets
    -0.64
     Reeves
    -0.64
     buck
    -0.64
     beads
    -0.62
     limp
    -0.62
     sunset
    -0.61
    POSITIVE LOGITS
    generated
    1.23
    friendly
    1.19
    driven
    1.14
    oriented
    1.09
    favorite
    1.09
    centric
    1.07
    controlled
    1.05
    facing
    1.05
    centered
    1.02
    focused
    1.01
    Activations Density 0.061%

    No Known Activations