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. 21383
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bo" in the text

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    377
    +0.12
    0.6%
    728
    +0.11
    0.5%
    122
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.12
    0.01
    444
    +0.11
    0.01
    376
    +0.11
    0.01
    Negative Logits
    ional
    -0.78
    orial
    -0.76
    uality
    -0.75
    arians
    -0.70
    UAL
    -0.69
    baugh
    -0.64
    mary
    -0.64
    OPE
    -0.63
    itations
    -0.62
    itates
    -0.61
    POSITIVE LOGITS
    olean
    1.30
    leans
    1.04
    gey
    0.99
    ilers
    0.97
    oru
    0.92
    zzi
    0.92
    xon
    0.90
    ever
    0.90
    OTH
    0.89
    iler
    0.87
    Activations Density 0.013%

    No Known Activations