© 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. 26781
    Prev
    Next
    INDEX
    Explanations

    specific titles and identifiers related to creators and their rankings or performances

    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
    323
    +0.11
    0.5%
    447
    +0.10
    0.5%
    193
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.11
    0.03
    6
    +0.10
    0.03
    640
    +0.10
    0.03
    Negative Logits
    SPONSORED
    -0.96
     convictions
    -0.79
    ¢
    -0.75
     relate
    -0.73
     resolves
    -0.72
     exposures
    -0.70
     ¶
    -0.69
    icultural
    -0.69
     stemmed
    -0.68
     fiscal
    -0.68
    POSITIVE LOGITS
    76561
    1.03
    Anonymous
    0.92
     john
    0.90
     Nek
    0.90
    mega
    0.89
    jay
    0.85
    mr
    0.85
     Markus
    0.84
    nin
    0.84
     Lil
    0.83
    Activations Density 0.084%

    No Known Activations