© 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. 11848
    Prev
    Next
    INDEX
    Explanations

    links or references to additional content such as articles or stories

    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
    373
    +0.12
    0.6%
    218
    +0.11
    0.5%
    38
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.12
    0.02
    472
    +0.11
    0.02
    316
    +0.09
    0.02
    Negative Logits
     DRAG
    -0.61
     stuffing
    -0.59
    ierrez
    -0.59
     Pros
    -0.58
     theoretically
    -0.58
     capitals
    -0.56
    erate
    -0.56
     rounding
    -0.56
     buggy
    -0.55
     sizing
    -0.55
    POSITIVE LOGITS
    646
    0.92
    shared
    0.91
    cb
    0.89
    tnc
    0.89
    264
    0.88
    297
    0.87
    cp
    0.87
    198
    0.84
    195
    0.84
    193
    0.83
    Activations Density 0.057%

    No Known Activations