© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18912
    Prev
    Next
    INDEX
    Explanations

    people's 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_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
    480
    +0.39
    2.1%
    447
    +0.34
    1.8%
    481
    +0.27
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.39
    0.07
    189
    +0.34
    0.06
    480
    +0.27
    0.01
    Negative Logits
     AAA
    -0.53
    amazon
    -0.52
     CET
    -0.51
     local
    -0.50
     Thumbnails
    -0.50
    acebook
    -0.50
    ãĥ¼ãĥĨ
    -0.48
    give
    -0.47
     *.
    -0.47
     pse
    -0.46
    POSITIVE LOGITS
    berger
    0.72
     testified
    0.72
     AFB
    0.71
    's
    0.69
    berg
    0.69
     County
    0.69
     et
    0.68
    ston
    0.68
    stein
    0.66
     agrees
    0.66
    Activations Density 0.303%

    No Known Activations