© 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. 11016
    Prev
    Next
    INDEX
    Explanations

    comments and corrections within a text or document

    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
    756
    +0.12
    0.5%
    400
    +0.12
    0.5%
    230
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.09
    679
    +0.12
    0.09
    255
    +0.09
    0.07
    Negative Logits
     affili
    -0.81
     persever
    -0.72
     enduring
    -0.72
     rehabilit
    -0.70
     millennium
    -0.67
     nurt
    -0.67
     temperament
    -0.65
     waged
    -0.65
     collabor
    -0.65
     accol
    -0.64
    POSITIVE LOGITS
     Meaning
    1.35
     Previously
    1.23
     Presumably
    1.19
     Normally
    1.16
     Whereas
    1.09
     Whilst
    1.04
     Apparently
    1.04
     Therefore
    1.02
     Again
    1.01
     Which
    1.01
    Activations Density 0.514%

    No Known Activations