© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 3051
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and player names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    431
    +0.11
    0.5%
    590
    +0.11
    0.5%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.11
    0.07
    232
    +0.11
    0.07
    431
    +0.10
    0.06
    Negative Logits
     Halls
    -0.66
     Tart
    -0.64
     Sidd
    -0.58
     bottleneck
    -0.58
     Soldiers
    -0.58
    theless
    -0.57
     Tess
    -0.57
     Leilan
    -0.57
     comprom
    -0.56
     moderator
    -0.56
    POSITIVE LOGITS
    .,
    1.75
    .?
    1.36
    .,"
    1.33
    orporated
    1.32
    .;
    1.27
    .:
    1.24
    ./
    1.17
    arcer
    1.16
    .),
    1.14
    eter
    1.13
    Activations Density 0.642%

    No Known Activations