© 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 24576
    9. 8-RES_FS24576-JB
    11. 7750
    Prev
    Next
    INDEX
    Explanations

    proper names, especially names related to the Star Wars franchise

    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
    447
    +0.16
    0.7%
    481
    +0.14
    0.6%
    371
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.16
    0.05
    659
    +0.14
    0.05
    326
    +0.09
    0.05
    Negative Logits
    IENT
    -0.81
     petroleum
    -0.76
    lishes
    -0.75
    ailability
    -0.73
    GBT
    -0.71
    itutional
    -0.70
     maturity
    -0.69
     qualitative
    -0.69
    ordable
    -0.68
     campuses
    -0.68
    POSITIVE LOGITS
     Kenobi
    1.13
     himself
    1.02
     Himself
    1.00
     Jr
    0.98
     Skywalker
    0.97
    buster
    0.96
     Statue
    0.94
     statue
    0.91
     Returns
    0.91
     aka
    0.91
    Activations Density 0.255%

    No Known Activations