© 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. 19411
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical information and documentation

    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
    362
    +0.18
    0.8%
    393
    +0.18
    0.8%
    159
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.09
    385
    +0.18
    0.07
    159
    +0.14
    0.06
    Negative Logits
    jee
    -0.74
    agree
    -0.71
    Cho
    -0.70
    qi
    -0.68
    worn
    -0.68
    cles
    -0.66
    ledge
    -0.65
    ibl
    -0.64
    flows
    -0.64
    agy
    -0.64
    POSITIVE LOGITS
     sake
    1.83
     purposes
    1.45
     upcoming
    1.30
     remainder
    1.24
     foreseeable
    1.22
     purpose
    1.20
     entire
    1.04
     duration
    1.01
     sexes
    1.00
     entirety
    0.99
    Activations Density 0.216%

    No Known Activations