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. 23701
    Prev
    Next
    INDEX
    Explanations

    references to the "Red" teams or entities, particularly in sports 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
    459
    +0.15
    0.7%
    16
    +0.13
    0.6%
    232
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.15
    0.03
    232
    +0.13
    0.03
    459
    +0.11
    0.03
    Negative Logits
    ILA
    -0.73
    merce
    -0.73
    awaru
    -0.71
    Ö¼
    -0.71
    SPONSORED
    -0.71
     4090
    -0.68
    FAULT
    -0.68
     incorpor
    -0.68
    ilities
    -0.67
     Lank
    -0.65
    POSITIVE LOGITS
    eem
    1.25
    ucing
    1.24
    uces
    1.18
    uced
    1.14
    ucer
    1.10
    emption
    1.09
    irect
    1.09
    oubt
    1.09
    cliffe
    1.06
    neck
    1.05
    Activations Density 0.019%

    No Known Activations