© 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 24576
    9. 8-RES_FS24576-JB
    11. 7127
    Prev
    Next
    INDEX
    Explanations

    names of individuals or companies

    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
    +0.16
    0.7%
    228
    +0.11
    0.5%
    285
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.16
    0.01
    284
    +0.11
    0.01
    228
    +0.10
    0.01
    Negative Logits
    andise
    -0.86
     Yates
    -0.68
    SOURCE
    -0.67
     Dragonbound
    -0.66
    ãĤ®
    -0.63
     Pillar
    -0.63
    itance
    -0.63
     Hilton
    -0.62
    okin
    -0.62
    FUL
    -0.62
    POSITIVE LOGITS
    erers
    1.05
    reth
    0.97
    ered
    0.97
    erer
    0.89
    er
    0.88
    ering
    0.87
    rag
    0.84
    ung
    0.84
    roid
    0.84
    enstein
    0.83
    Activations Density 0.028%

    No Known Activations