© 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. 285
    Prev
    Next
    INDEX
    Explanations

    mentions of the majority or prevalence of a certain group or situation

    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
    393
    +0.15
    0.7%
    71
    +0.11
    0.5%
    608
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.15
    0.04
    9
    +0.11
    0.03
    409
    +0.10
    0.03
    Negative Logits
    resy
    -0.72
    dayName
    -0.71
    sort
    -0.70
    acus
    -0.67
    abl
    -0.66
    cule
    -0.65
    usp
    -0.64
    dl
    -0.64
    é¾įåĸļ士
    -0.63
     lest
    -0.63
    POSITIVE LOGITS
     respondents
    0.90
     occurrences
    0.89
     Americans
    0.87
     cases
    0.85
     people
    0.84
     households
    0.83
     those
    0.79
     casualties
    0.79
     fatalities
    0.77
     applicants
    0.74
    Activations Density 0.083%

    No Known Activations