© 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 24576
    9. 8-RES_FS24576-JB
    11. 8881
    Prev
    Next
    INDEX
    Explanations

    descriptions of events or actions involving specific individuals and locations, such as accidents, trials, and police-related incidents

    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
    593
    +0.11
    0.5%
    369
    +0.11
    0.5%
    241
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    652
    +0.11
    0.05
    593
    +0.11
    0.05
    369
    +0.11
    0.04
    Negative Logits
    utenberg
    -0.84
     Diss
    -0.76
    女
    -0.75
    wu
    -0.72
    ozo
    -0.72
    owment
    -0.70
     ppm
    -0.69
     Discipline
    -0.68
     pores
    -0.67
    imaru
    -0.66
    POSITIVE LOGITS
     vehicles
    1.59
     cars
    1.57
     vehicle
    1.53
     passenger
    1.47
     taxis
    1.44
     automobiles
    1.40
     aircraft
    1.38
     automobile
    1.37
     Vehicle
    1.35
     trucks
    1.35
    Activations Density 0.720%

    No Known Activations