© 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. 24254
    Prev
    Next
    INDEX
    Explanations

    references to demographic groups and their statistics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    745
    +0.11
    0.5%
    708
    +0.11
    0.5%
    648
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.04
    15
    +0.11
    0.04
    224
    +0.10
    0.04
    Negative Logits
    RAW
    -0.71
    ollah
    -0.70
     extraord
    -0.69
    unity
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    ãģĻ
    -0.63
    ãĥ¥
    -0.63
    kefeller
    -0.62
     interchange
    -0.60
     endless
    -0.59
    POSITIVE LOGITS
     surveyed
    1.46
     polled
    1.37
     interviewed
    0.92
     respondents
    0.89
     sampled
    0.87
     disapprove
    0.87
     diagnosed
    0.80
     worldwide
    0.80
     admitted
    0.79
     tested
    0.79
    Activations Density 0.179%

    No Known Activations