© 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. 18438
    Prev
    Next
    INDEX
    Explanations

    questions starting with 'what'

    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
    668
    +0.09
    0.4%
    633
    +0.08
    0.4%
    555
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.09
    0.03
    434
    +0.08
    0.03
    632
    +0.08
    0.02
    Negative Logits
    Interstitial
    -0.81
    DERR
    -0.74
    mens
    -0.73
    renheit
    -0.70
    apsed
    -0.70
    Said
    -0.69
    agos
    -0.66
    anus
    -0.66
    uffer
    -0.65
    ache
    -0.64
    POSITIVE LOGITS
    ?
    0.95
    ?'"
    0.90
    ?'
    0.89
     exactly
    0.87
    !?
    0.85
    ?"
    0.84
    ?".
    0.84
    ?ãĢį
    0.81
    ?",
    0.81
     happens
    0.79
    Activations Density 0.050%

    No Known Activations