© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    statistical and scientific terms related to a study or experiment

    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
    545
    +0.14
    0.6%
    575
    +0.10
    0.4%
    689
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.05
    545
    +0.10
    0.03
    469
    +0.09
    0.03
    Negative Logits
    iquette
    -0.93
    tainment
    -0.83
    女
    -0.80
    rency
    -0.77
    INESS
    -0.77
    é»Ĵ
    -0.76
     meanings
    -0.74
    Business
    -0.72
    Flags
    -0.72
     totem
    -0.70
    POSITIVE LOGITS
     vaccinated
    1.05
     experimental
    0.98
     chronically
    0.95
     diabetic
    0.95
     infected
    0.94
     allergic
    0.94
     circadian
    0.94
     tested
    0.93
     immune
    0.92
     Alzheimer
    0.92
    Activations Density 0.206%

    No Known Activations