© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    mentions of social issues and controversies

    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
    637
    +0.11
    0.5%
    16
    +0.10
    0.4%
    475
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    412
    +0.10
    0.06
    616
    +0.10
    0.06
    Negative Logits
     Yorkers
    -0.76
    paio
    -0.68
    orsi
    -0.68
    atism
    -0.63
    mates
    -0.61
     mates
    -0.60
    BILITIES
    -0.60
    olicited
    -0.60
    ewitness
    -0.59
     Flavoring
    -0.59
    POSITIVE LOGITS
     vicinity
    1.24
     realm
    1.16
     arena
    1.07
     context
    1.00
     midst
    0.99
     confines
    0.98
     attic
    0.97
     aisle
    0.97
    osphere
    0.97
     guise
    0.96
    Activations Density 0.505%

    No Known Activations