© 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. 23991
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to significant events or references

    oai_token-act-pair · gpt-4o-miniTriggered 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
    480
    +0.48
    2.4%
    266
    +0.12
    0.6%
    720
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.01
    266
    +0.12
    0.06
    659
    +0.08
    0.05
    Negative Logits
    ocobo
    -0.69
    ],"
    -0.68
    uminati
    -0.57
    âĹ¼
    -0.57
    foundland
    -0.55
     Mehran
    -0.54
    umbn
    -0.54
    Downloadha
    -0.53
    strument
    -0.53
     beginning
    -0.53
    POSITIVE LOGITS
    cknowled
    0.75
    itionally
    0.70
    ually
    0.66
    hetically
    0.64
    ONSORED
    0.64
    quartered
    0.63
    cially
    0.63
    wise
    0.61
     Locations
    0.61
     Features
    0.61
    Activations Density 0.386%

    No Known Activations