© 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 24576
    5. 8-RES_FS24576-JB
    6. 23931
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered 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
    731
    +0.12
    0.6%
    697
    +0.12
    0.5%
    296
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    659
    +0.12
    0.03
    627
    +0.12
    0.02
    Negative Logits
     Petersen
    -0.86
     PW
    -0.85
     Perkins
    -0.80
     whist
    -0.78
     Woodward
    -0.78
     Winn
    -0.75
    isu
    -0.74
     Penguins
    -0.74
     Pioneer
    -0.72
     Peck
    -0.72
    POSITIVE LOGITS
    al
    1.66
    AL
    1.51
    alis
    1.37
    alist
    1.32
    als
    1.31
    alm
    1.22
    alam
    1.22
    alian
    1.21
    ala
    1.17
    ali
    1.17
    Activations Density 0.096%

    No Known Activations