© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17784
    Prev
    Next
    INDEX
    Explanations

    legal terms and descriptions related to law enforcement

    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
    480
    +0.28
    1.4%
    640
    +0.24
    1.2%
    94
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.16
    94
    +0.24
    0.12
    143
    +0.10
    0.08
    Negative Logits
    senal
    -0.82
    awei
    -0.73
     aging
    -0.65
    heit
    -0.61
    ensibly
    -0.60
     ageing
    -0.60
    ļé
    -0.59
    ĥ
    -0.58
    aturdays
    -0.57
    culus
    -0.57
    POSITIVE LOGITS
    Scroll
    0.82
     Related
    0.71
    ↵
    0.68
     Franch
    0.68
     Imran
    0.67
     Reporter
    0.66
     Debor
    0.64
     Hitchcock
    0.64
    SEE
    0.63
     Universities
    0.63
    Activations Density 0.465%

    No Known Activations