© 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. 12079
    Prev
    Next
    INDEX
    Explanations

    references to park-related activities and locations

    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
    481
    +0.16
    0.8%
    459
    +0.15
    0.7%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.16
    0.02
    270
    +0.15
    0.02
    575
    +0.11
    0.02
    Negative Logits
    xit
    -0.71
     dilig
    -0.63
     Qiao
    -0.63
     vowel
    -0.60
     abnormal
    -0.58
     microscopic
    -0.58
     flawed
    -0.58
     diagnoses
    -0.57
     faulty
    -0.57
     agon
    -0.57
    POSITIVE LOGITS
    conservancy
    1.10
    park
    1.08
    land
    0.98
    lands
    0.95
    our
    0.93
    goers
    0.90
    grounds
    0.86
     park
    0.85
    lot
    0.83
    keeper
    0.82
    Activations Density 0.028%

    No Known Activations