© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    words related to the description or history of musical bands

    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
    373
    +0.11
    0.5%
    657
    +0.10
    0.4%
    477
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    701
    +0.10
    0.01
    652
    +0.09
    0.01
    Negative Logits
    mob
    -0.70
    951
    -0.68
    bub
    -0.65
    sense
    -0.64
    icter
    -0.63
    nyder
    -0.63
    ãĤ§
    -0.62
    olesc
    -0.62
    vez
    -0.61
    ãĤ£
    -0.60
    POSITIVE LOGITS
    eer
    0.96
    eers
    0.95
    arist
    0.92
    ridge
    0.86
    uit
    0.78
    arium
    0.77
    addons
    0.76
    eering
    0.74
    ements
    0.73
    ially
    0.72
    Activations Density 0.018%

    No Known Activations