© 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 24576
    9. 8-RES_FS24576-JB
    11. 10506
    Prev
    Next
    INDEX
    Explanations

    instances where people or players are mentioned

    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
    91
    +0.09
    0.4%
    462
    +0.09
    0.4%
    496
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.09
    0.03
    241
    +0.09
    0.03
    86
    +0.09
    0.03
    Negative Logits
     Deadly
    -0.73
    ILA
    -0.67
    rompt
    -0.65
     Loch
    -0.63
    MpServer
    -0.61
    =]
    -0.60
     Sanctuary
    -0.59
     retribution
    -0.59
    rss
    -0.58
     Fury
    -0.57
    POSITIVE LOGITS
     perceive
    0.97
     instinctively
    0.96
     prefer
    0.96
     confuse
    0.93
     nowadays
    0.91
     agree
    0.89
     realize
    0.89
     equate
    0.87
     assume
    0.86
     realise
    0.84
    Activations Density 0.109%

    No Known Activations