© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 761
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    89
    +0.11
    0.5%
    351
    +0.11
    0.5%
    721
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.11
    0.06
    343
    +0.11
    0.05
    89
    +0.09
    0.05
    Negative Logits
    naires
    -0.80
     Flavoring
    -0.78
    scl
    -0.77
     Seym
    -0.74
    ãĥĥãĥĪ
    -0.73
    xual
    -0.72
    é¾įå¥ij士
    -0.71
    enance
    -0.71
     Lans
    -0.69
    edIn
    -0.68
    POSITIVE LOGITS
    ousel
    1.50
    penter
    1.31
    riages
    1.29
    olina
    1.13
    rera
    1.12
    riage
    1.12
    negie
    1.10
     dealership
    0.98
    riers
    0.92
    olyn
    0.91
    Activations Density 0.526%

    No Known Activations