© 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 24576
    9. 8-RES_FS24576-JB
    11. 7902
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.24
    1.2%
    481
    +0.19
    0.9%
    640
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.24
    0.07
    640
    +0.19
    0.07
    176
    +0.13
    0.04
    Negative Logits
    ensibly
    -0.83
    usting
    -0.64
     shrunk
    -0.63
     shrinking
    -0.58
     overpowered
    -0.57
     majesty
    -0.57
     flourishing
    -0.56
     snowball
    -0.56
     rightfully
    -0.55
    omics
    -0.55
    POSITIVE LOGITS
     Lastly
    1.04
     =================================================================
    1.00
     ********************************
    1.00
    ================================================================
    0.92
     =================================
    0.91
     Finally
    0.89
     Alternatively
    0.88
     Similarly
    0.86
     Additionally
    0.85
     Else
    0.82
    Activations Density 0.241%

    No Known Activations