© 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. 16897
    Prev
    Next
    INDEX
    Explanations

    company names and product names related to technology

    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
    480
    +0.23
    1.1%
    481
    +0.11
    0.5%
    709
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.08
    57
    +0.11
    0.06
    224
    +0.11
    0.06
    Negative Logits
    rodu
    -0.59
     eternity
    -0.58
    tnc
    -0.57
    aer
    -0.56
    runtime
    -0.55
    ixir
    -0.55
     ancest
    -0.54
    EStreamFrame
    -0.54
     dece
    -0.52
    mean
    -0.52
    POSITIVE LOGITS
     meanwhile
    0.91
     likewise
    0.77
     reacted
    0.70
    IRC
    0.67
     forbid
    0.67
     intervened
    0.66
     similarly
    0.63
     opted
    0.62
     dominates
    0.62
     reacts
    0.61
    Activations Density 0.458%

    No Known Activations