© 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. 8784
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and scientific studies, particularly focusing on immunology and lab experiments

    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
    484
    +0.12
    0.6%
    481
    +0.11
    0.5%
    393
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.07
    0
    +0.11
    0.06
    128
    +0.10
    0.05
    Negative Logits
    uel
    -0.73
    ummer
    -0.72
    \-
    -0.71
    umat
    -0.70
    laughter
    -0.66
    IRE
    -0.66
    usercontent
    -0.65
    adra
    -0.65
    AG
    -0.64
    Street
    -0.64
    POSITIVE LOGITS
     compares
    1.16
     discusses
    1.07
     how
    1.06
     concludes
    1.03
     examines
    1.00
     compare
    0.97
     adjusts
    0.97
     reveals
    0.96
     conclude
    0.94
     illustrate
    0.92
    Activations Density 0.313%

    No Known Activations