© 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 EvalsExportsinterp-engineNEWAPI 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. 14295
    Prev
    Next
    INDEX
    Explanations

    information related to a dangerous swallowing hazard

    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
    571
    +0.13
    0.6%
    271
    +0.13
    0.6%
    461
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.13
    0.02
    571
    +0.13
    0.01
    326
    +0.10
    0.01
    Negative Logits
    senal
    -0.77
    ements
    -0.73
    abouts
    -0.70
    jah
    -0.69
    romy
    -0.66
    semble
    -0.65
    Hist
    -0.65
    efeated
    -0.64
    joining
    -0.62
    Tech
    -0.62
    POSITIVE LOGITS
     swallowing
    0.97
     swallow
    0.95
     gum
    0.92
    ipes
    0.84
     saliva
    0.83
    ibility
    0.81
     popcorn
    0.79
    ibles
    0.78
    hered
    0.76
    tails
    0.76
    Activations Density 0.030%

    No Known Activations