© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    words related to events or locations taking place on specific dates

    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
    590
    +0.10
    0.4%
    447
    +0.10
    0.4%
    542
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.10
    0.02
    439
    +0.10
    0.02
    531
    +0.10
    0.02
    Negative Logits
    acked
    -0.73
    iciency
    -0.72
    definition
    -0.70
    orters
    -0.68
    aldo
    -0.67
    ipedia
    -0.66
    ickets
    -0.65
    isle
    -0.63
    nor
    -0.60
    iscovery
    -0.60
    POSITIVE LOGITS
     indoors
    0.84
     concurrently
    0.82
    actionDate
    0.82
     atop
    0.81
     amidst
    0.81
     outdoors
    0.79
     inside
    0.79
    uate
    0.78
     elsewhere
    0.78
     aboard
    0.72
    Activations Density 0.033%

    No Known Activations