© 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. 9477
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to software installation

    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
    245
    +0.11
    0.5%
    417
    +0.11
    0.5%
    476
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.11
    0.02
    245
    +0.11
    0.02
    582
    +0.11
    0.02
    Negative Logits
    sem
    -0.82
    ĸļ
    -0.74
    hirt
    -0.73
    ombs
    -0.70
    emic
    -0.70
    obin
    -0.68
    fax
    -0.68
    pee
    -0.67
    usable
    -0.65
    geon
    -0.65
    POSITIVE LOGITS
     installs
    0.78
    antly
    0.73
     installer
    0.71
     installation
    0.70
     install
    0.70
    ç¥ŀ
    0.70
     installed
    0.66
     installations
    0.66
     Krypt
    0.66
     blockers
    0.66
    Activations Density 0.081%

    No Known Activations