© 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. 13052
    Prev
    Next
    INDEX
    Explanations

    safety-related information and trends in road safety

    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
    97
    +0.12
    0.5%
    303
    +0.10
    0.5%
    650
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.02
    97
    +0.10
    0.01
    488
    +0.10
    0.01
    Negative Logits
    abase
    -0.93
    DN
    -0.81
    ghazi
    -0.80
    mberg
    -0.77
    TOP
    -0.77
    nington
    -0.76
    anan
    -0.71
    acea
    -0.68
    imens
    -0.68
    mong
    -0.67
    POSITIVE LOGITS
     spiral
    0.97
    ward
    0.85
    wards
    0.83
     trajectory
    0.83
     curv
    0.82
     traject
    0.81
    most
    0.81
    volent
    0.78
    bound
    0.77
     slope
    0.77
    Activations Density 0.028%

    No Known Activations