© 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. 26726
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols

    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
    699
    +0.11
    0.5%
    61
    +0.10
    0.4%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.01
    728
    +0.10
    0.01
    594
    +0.09
    0.01
    Negative Logits
     deaf
    -0.73
    xus
    -0.70
    chnology
    -0.66
     satell
    -0.66
     tremend
    -0.64
    stal
    -0.64
     misunder
    -0.64
     Sapphire
    -0.63
     deduct
    -0.63
     mesmer
    -0.62
    POSITIVE LOGITS
    оÐ
    1.08
    ÑĢ
    1.02
    Ñĥ
    0.97
    о
    0.96
    е
    0.89
    л
    0.88
    enance
    0.87
    а
    0.86
    rito
    0.84
    éĹ
    0.84
    Activations Density 0.003%

    No Known Activations