© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    mentions of accidents, disasters, or emergencies

    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
    640
    +0.11
    0.5%
    468
    +0.10
    0.5%
    263
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.11
    0.02
    468
    +0.10
    0.02
    78
    +0.10
    0.02
    Negative Logits
    icrobial
    -0.76
    ROR
    -0.73
    itia
    -0.71
    rolog
    -0.69
    addon
    -0.69
    Ľ
    -0.67
    eele
    -0.65
    arov
    -0.65
    achu
    -0.65
    ipedia
    -0.64
    POSITIVE LOGITS
    worthiness
    1.13
     Dive
    0.93
     crashes
    0.90
     crash
    0.87
    course
    0.81
     wreck
    0.80
     dumps
    0.78
     Course
    0.76
     Crash
    0.74
    Crash
    0.73
    Activations Density 0.035%

    No Known Activations