© 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. 24110
    Prev
    Next
    INDEX
    Explanations

    references to viewing or experiencing something

    oai_token-act-pair · gpt-4o-miniTriggered 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
    395
    +0.10
    0.5%
    426
    +0.10
    0.4%
    84
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.10
    0.04
    240
    +0.10
    0.04
    403
    +0.09
    0.04
    Negative Logits
    externalActionCode
    -0.78
    currency
    -0.72
    trap
    -0.72
     agric
    -0.66
    onto
    -0.64
    adding
    -0.64
    hesion
    -0.63
    recy
    -0.62
    ÃŃa
    -0.62
     suscept
    -0.61
    POSITIVE LOGITS
    dust
    1.17
     firsthand
    0.87
    awed
    0.81
     him
    0.77
     pictures
    0.77
     glimps
    0.76
    lights
    0.75
     flashes
    0.74
     them
    0.74
     visions
    0.73
    Activations Density 0.071%

    No Known Activations