© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8746
    Prev
    Next
    INDEX
    Explanations

    information related to sports injuries, especially those involving knees

    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
    135
    +0.10
    0.5%
    629
    +0.10
    0.5%
    405
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.10
    0.03
    281
    +0.10
    0.03
    319
    +0.09
    0.03
    Negative Logits
     sidx
    -0.84
    Reviewer
    -0.82
    istas
    -0.78
     sqor
    -0.77
    ellig
    -0.76
     households
    -0.74
    onym
    -0.74
    eworld
    -0.73
    leground
    -0.72
    illions
    -0.72
    POSITIVE LOGITS
     tendon
    1.34
     Surgery
    1.22
     surgery
    1.18
     lig
    1.15
     injury
    1.13
     injuries
    1.09
     Injury
    1.05
     amput
    1.04
     inflammation
    1.04
     surgeries
    1.03
    Activations Density 0.331%

    No Known Activations