© 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. 45855
    Prev
    Next
    INDEX
    Explanations

    references to large corporations or entities

    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
    623
    +0.15
    0.7%
    129
    +0.10
    0.5%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.15
    0.06
    117
    +0.10
    0.04
    65
    +0.10
    0.04
    Negative Logits
     Reincarnated
    -0.76
    yrinth
    -0.72
     Emin
    -0.72
    DragonMagazine
    -0.66
    cia
    -0.66
    veyard
    -0.65
    IRC
    -0.65
    ILA
    -0.64
     Cheong
    -0.63
    Dialogue
    -0.63
    POSITIVE LOGITS
    oted
    1.18
    gest
    1.09
    wig
    1.07
     bucks
    0.94
    ger
    0.91
    amy
    0.89
     chunk
    0.88
     chunks
    0.86
    GER
    0.86
     ol
    0.85
    Activations Density 0.045%

    No Known Activations