© 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. 6609
    Prev
    Next
    INDEX
    Explanations

    words related to food ingredients and cooking techniques

    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
    738
    +0.12
    0.5%
    286
    +0.12
    0.5%
    101
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.12
    0.02
    738
    +0.12
    0.01
    232
    +0.11
    0.01
    Negative Logits
     lapse
    -0.73
     conspicuous
    -0.71
     Polar
    -0.69
     ransom
    -0.66
     Conrad
    -0.65
     appropriation
    -0.65
     pole
    -0.64
     compl
    -0.63
    croft
    -0.63
     bravery
    -0.60
    POSITIVE LOGITS
    arella
    1.43
    ucc
    1.16
    zz
    1.07
    etta
    0.99
    hou
    0.98
    erella
    0.96
    eret
    0.96
    arro
    0.96
    ella
    0.94
    iere
    0.92
    Activations Density 0.019%

    No Known Activations