© 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 24576
    9. 8-RES_FS24576-JB
    11. 20668
    Prev
    Next
    INDEX
    Explanations

    college football team names along with their associated scores

    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
    373
    +0.20
    0.9%
    573
    +0.11
    0.5%
    316
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.20
    0.03
    469
    +0.11
    0.02
    707
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.77
    EStreamFrame
    -0.74
    Interstitial
    -0.74
    PIN
    -0.71
    Thumbnail
    -0.64
    Temp
    -0.63
    Products
    -0.61
    Contribut
    -0.59
    value
    -0.58
    pire
    -0.57
    POSITIVE LOGITS
     39
    1.27
     49
    1.27
     63
    1.24
     33
    1.23
     48
    1.22
     53
    1.22
     56
    1.20
     54
    1.20
     57
    1.19
     36
    1.19
    Activations Density 0.084%

    No Known Activations