© 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 EvalsExportsinterp-engineNEWAPI 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. 16107
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and culture

    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
    481
    +0.10
    0.4%
    690
    +0.09
    0.4%
    710
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.10
    0.05
    651
    +0.09
    0.05
    680
    +0.09
    0.03
    Negative Logits
    æ©
    -0.70
    fax
    -0.63
     wink
    -0.62
    animate
    -0.61
    stood
    -0.58
    Flag
    -0.57
     consulate
    -0.57
     symbol
    -0.57
    enery
    -0.57
    igslist
    -0.56
    POSITIVE LOGITS
     installment
    1.08
     installments
    1.02
     roundup
    0.94
    isode
    0.92
     series
    0.89
     delve
    0.88
    PDATED
    0.85
     Discussion
    0.85
    Interview
    0.85
    series
    0.84
    Activations Density 0.347%

    No Known Activations