© 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 12288
    5. 8-RES_FS12288-JB
    6. 1763
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    106
    +0.15
    0.7%
    481
    +0.10
    0.5%
    755
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.05
    106
    +0.10
    0.05
    232
    +0.10
    0.04
    Negative Logits
     msec
    -0.70
     Normandy
    -0.68
    AMS
    -0.66
     SPD
    -0.66
     Phillies
    -0.66
     Hitchcock
    -0.65
    axter
    -0.64
     Redux
    -0.64
     recess
    -0.63
     parole
    -0.61
    POSITIVE LOGITS
    jiang
    1.49
     Xia
    1.48
    jing
    1.48
     Jing
    1.45
     Bei
    1.43
     Guang
    1.40
     Jian
    1.39
     Xiang
    1.39
    zhou
    1.38
     Yuan
    1.38
    Activations Density 0.165%

    No Known Activations