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. 8414
    Prev
    Next
    INDEX
    Explanations

    spell cards and game mechanics mentioned in Yu-Gi-Oh! related 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
    314
    +0.18
    0.8%
    526
    +0.11
    0.5%
    597
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.05
    326
    +0.11
    0.04
    597
    +0.11
    0.03
    Negative Logits
    uana
    -0.68
     reper
    -0.65
    Downloadha
    -0.64
     insol
    -0.61
    senal
    -0.59
     traged
    -0.57
     territ
    -0.55
     proble
    -0.55
    ggle
    -0.55
     necessities
    -0.54
    POSITIVE LOGITS
    ed
    2.80
    ing
    1.83
    edly
    1.80
    edIn
    1.62
    ED
    1.43
    ered
    1.39
    eds
    1.32
    ated
    1.24
    eers
    1.21
    ened
    1.20
    Activations Density 0.201%

    No Known Activations