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 49152
    5. 8-RES_FS49152-JB
    6. 43304
    Prev
    Next
    INDEX
    Explanations

    references to specific video game titles and franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    476
    +0.12
    0.5%
    549
    +0.12
    0.5%
    530
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.12
    0.03
    667
    +0.12
    0.03
    232
    +0.10
    0.03
    Negative Logits
    jri
    -0.82
    unicip
    -0.78
    gie
    -0.72
     spons
    -0.71
     eleph
    -0.69
    nesday
    -0.69
     bott
    -0.68
    ntil
    -0.68
     stopp
    -0.67
     Seym
    -0.67
    POSITIVE LOGITS
     Chronicles
    1.24
     Reborn
    1.14
     Rebirth
    1.12
     Crusade
    1.10
     Legends
    1.08
     Origins
    1.08
     Legacy
    1.07
     Underworld
    1.07
     Inquisition
    1.05
     Odyssey
    1.04
    Activations Density 0.083%

    No Known Activations