© 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 12288
    9. 8-RES_FS12288-JB
    11. 1624
    Prev
    Next
    INDEX
    Explanations

    references to car models and technical specifications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.13
    0.6%
    418
    +0.10
    0.5%
    552
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    435
    +0.10
    0.01
    236
    +0.10
    0.02
    Negative Logits
    ufact
    -1.01
    tical
    -0.75
    ously
    -0.74
    Downloadha
    -0.73
    taining
    -0.72
    theless
    -0.68
    sembly
    -0.67
     aver
    -0.67
    scrib
    -0.63
    idence
    -0.63
    POSITIVE LOGITS
    FO
    0.91
    opher
    0.85
    ECH
    0.83
    amera
    0.80
    ravis
    0.80
    TH
    0.79
    ourmet
    0.79
    GT
    0.79
    TER
    0.78
    LM
    0.78
    Activations Density 0.045%

    No Known Activations