© 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 49152
    9. 8-RES_FS49152-JB
    11. 45687
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "l."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    0.6%
    373
    +0.12
    0.6%
    154
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.14
    0.06
    439
    +0.12
    0.06
    157
    +0.11
    0.06
    Negative Logits
     elim
    -0.74
     scrim
    -0.70
     cob
    -0.69
     decomp
    -0.68
     convict
    -0.67
     glim
    -0.66
     simul
    -0.65
     pyramid
    -0.65
     reprodu
    -0.62
     scrut
    -0.62
    POSITIVE LOGITS
    s
    1.28
    ski
    1.12
    tsy
    1.06
    tal
    1.06
    tre
    1.04
    sin
    0.99
    til
    0.98
    sky
    0.94
    ship
    0.93
    thy
    0.93
    Activations Density 0.086%

    No Known Activations