© 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. 8531
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and political events

    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
    612
    +0.12
    0.5%
    405
    +0.10
    0.4%
    210
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.12
    0.02
    16
    +0.10
    0.02
    476
    +0.09
    0.01
    Negative Logits
     inherit
    -0.65
    orno
    -0.63
     currently
    -0.60
    pmwiki
    -0.59
    ombies
    -0.59
     Frankenstein
    -0.58
    /"
    -0.58
    afety
    -0.58
     WATCHED
    -0.57
    é¾įå¥ij士
    -0.57
    POSITIVE LOGITS
    cheon
    0.83
    than
    0.72
    itudes
    0.71
    itud
    0.70
    itiz
    0.70
    isode
    0.68
    imester
    0.67
    versely
    0.66
    naissance
    0.65
    elight
    0.65
    Activations Density 0.047%

    No Known Activations