Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2741
    Prev
    Next
    INDEX
    Explanations

    information or news articles related to Thailand

    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
    496
    +0.13
    0.6%
    701
    +0.12
    0.5%
    742
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.06
    701
    +0.12
    0.05
    742
    +0.11
    0.04
    Negative Logits
    ITED
    -0.69
    ãģ®éŃĶ
    -0.69
    âĸ¬âĸ¬
    -0.68
     shorth
    -0.67
    ATION
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
     Petraeus
    -0.63
    Tokens
    -0.61
    ATIONS
    -0.61
     Reloaded
    -0.60
    POSITIVE LOGITS
    irteen
    1.34
    reshold
    1.28
    ieving
    1.19
    orns
    1.18
    istle
    1.18
    umbnail
    1.15
    orne
    1.15
    ttp
    1.14
    ought
    1.12
    irst
    1.12
    Activations Density 0.466%

    No Known Activations