© 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 49152
    9. 8-RES_FS49152-JB
    11. 42866
    Prev
    Next
    INDEX
    Explanations

    future occurrences of events and conferences with associated dates and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    677
    +0.12
    0.6%
    749
    +0.10
    0.4%
    20
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.12
    0.04
    749
    +0.10
    0.04
    310
    +0.09
    0.03
    Negative Logits
    otomy
    -0.78
     clipboard
    -0.71
     divorce
    -0.68
     extraction
    -0.65
     ransom
    -0.64
     deterioration
    -0.63
     mistakes
    -0.63
     corrections
    -0.63
     Translation
    -0.63
     amput
    -0.63
    POSITIVE LOGITS
     attendees
    1.06
     hosted
    1.05
    goers
    1.03
     EVENT
    1.00
     organizers
    0.98
     Thurs
    0.94
     event
    0.92
     venue
    0.92
     kickoff
    0.91
     organisers
    0.88
    Activations Density 0.149%

    No Known Activations