© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41627
    Prev
    Next
    INDEX
    Explanations

    technical specifications and types of content

    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
    706
    +0.10
    0.5%
    671
    +0.10
    0.5%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.01
    603
    +0.10
    0.01
    699
    +0.09
    0.01
    Negative Logits
    uckland
    -0.79
    orsi
    -0.77
    ocrates
    -0.70
    reys
    -0.67
     pupils
    -0.66
    DERR
    -0.65
    rey
    -0.64
     whom
    -0.64
    kefeller
    -0.64
     Adelaide
    -0.64
    POSITIVE LOGITS
    submit
    0.90
    application
    0.90
    rss
    0.81
    AUT
    0.76
     MED
    0.75
     MV
    0.75
    fixed
    0.70
     MT
    0.69
     TEXT
    0.69
    widget
    0.68
    Activations Density 0.020%

    No Known Activations