© 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 EvalsExportsinterp-engineNEWAPI 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. 45428
    Prev
    Next
    INDEX
    Explanations

    references to time or sequences of events following specific moments

    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
    218
    +0.10
    0.5%
    616
    +0.09
    0.4%
    172
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.10
    0.05
    172
    +0.09
    0.04
    529
    +0.09
    0.04
    Negative Logits
    aez
    -0.75
    opsis
    -0.72
     constitu
    -0.71
    ãĥ¼
    -0.69
    esian
    -0.67
    enf
    -0.66
    cin
    -0.66
    cci
    -0.65
    oho
    -0.65
    kaya
    -0.63
    POSITIVE LOGITS
    noon
    1.10
    market
    0.96
     completing
    0.93
    wards
    0.93
     graduation
    0.89
     finishing
    0.89
    math
    0.89
    thought
    0.88
     sunset
    0.88
     takeoff
    0.86
    Activations Density 0.075%

    No Known Activations