© 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. 298
    Prev
    Next
    INDEX
    Explanations

    code-related details and file uploads

    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
    314
    +0.14
    0.7%
    496
    +0.11
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.14
    0.02
    158
    +0.11
    0.02
    345
    +0.10
    0.02
    Negative Logits
    ecause
    -0.70
     disg
    -0.66
     SAN
    -0.64
     nuts
    -0.64
     Lovecraft
    -0.62
     joints
    -0.61
     electrom
    -0.61
    xus
    -0.60
     Rabb
    -0.60
     NBN
    -0.59
    POSITIVE LOGITS
    ":"
    1.46
    ":"","
    1.26
    ":["
    1.25
    ":{"
    1.25
    ":
    1.17
    ":[
    1.12
    "]=>
    1.12
    Url
    1.09
    ":""},{"
    1.05
    ":[{"
    1.04
    Activations Density 0.053%

    No Known Activations