© 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. 8689
    Prev
    Next
    INDEX
    Explanations

    mentions of bottles

    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
    552
    +0.12
    0.5%
    240
    +0.12
    0.5%
    75
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.12
    0.02
    552
    +0.12
    0.02
    678
    +0.09
    0.01
    Negative Logits
    merce
    -0.89
    doms
    -0.80
    urities
    -0.68
    uli
    -0.67
    IFA
    -0.66
    tale
    -0.66
    ahime
    -0.66
    ancial
    -0.65
    roe
    -0.63
    yrinth
    -0.63
    POSITIVE LOGITS
     bottles
    1.21
     bottle
    1.14
     Bottle
    1.01
    Bott
    0.94
     Bott
    0.91
     opener
    0.86
     refill
    0.84
     cans
    0.83
     labelled
    0.83
     vodka
    0.80
    Activations Density 0.021%

    No Known Activations