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. 1129
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific text formatting such as citations, quotations, and script instructions

    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
    756
    +0.13
    0.6%
    158
    +0.11
    0.5%
    752
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.04
    30
    +0.11
    0.03
    760
    +0.11
    0.03
    Negative Logits
    ien
    -0.81
    nos
    -0.81
    ogi
    -0.79
    Merit
    -0.71
     Shepherd
    -0.71
    ication
    -0.71
    icates
    -0.67
    oday
    -0.67
    Weiss
    -0.67
    ications
    -0.65
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.77
    TER
    0.73
     Bhar
    0.72
     pixel
    0.71
    dat
    0.71
     TER
    0.71
     ;;
    0.70
    bara
    0.70
    ãĥĢ
    0.69
    Ĥ
    0.68
    Activations Density 0.310%

    No Known Activations