© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6306
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in a specific format

    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
    430
    +0.10
    0.4%
    89
    +0.10
    0.4%
    327
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.10
    0.03
    718
    +0.10
    0.04
    512
    +0.10
    0.03
    Negative Logits
     Flavoring
    -0.96
    artisan
    -0.86
    apons
    -0.75
     kindred
    -0.75
    uliffe
    -0.74
    urities
    -0.74
    olen
    -0.74
    rotein
    -0.74
    zech
    -0.73
    oyal
    -0.73
    POSITIVE LOGITS
     calendars
    1.16
     calendar
    1.16
     timeframe
    1.09
     postponed
    1.08
     shortest
    1.03
     TBD
    1.03
     Calendar
    1.01
     elapsed
    1.00
    GMT
    0.98
     clock
    0.98
    Activations Density 0.395%

    No Known Activations