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. 23042
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ong" in various contexts

    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
    106
    +0.13
    0.6%
    373
    +0.11
    0.5%
    701
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.13
    0.02
    106
    +0.11
    0.02
    659
    +0.11
    0.02
    Negative Logits
     ABE
    -0.69
    ãĥ¤
    -0.69
    ãĥ¡
    -0.69
    abouts
    -0.68
    ãĥ¯ãĥ³
    -0.68
     NASCAR
    -0.64
    ICAN
    -0.63
    endez
    -0.61
    IELD
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    POSITIVE LOGITS
    ratulations
    1.31
    regate
    1.15
    lasses
    1.14
    lass
    1.06
    regor
    0.97
    atana
    0.91
    ueless
    0.90
    uay
    0.90
    jiang
    0.87
    roup
    0.84
    Activations Density 0.021%

    No Known Activations