© 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. 18757
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective identity or shared experiences

    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
    167
    +0.13
    0.6%
    234
    +0.12
    0.5%
    585
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.04
    167
    +0.12
    0.02
    234
    +0.11
    0.04
    Negative Logits
     Kush
    -0.67
     gratification
    -0.65
     firsthand
    -0.64
     Cliff
    -0.63
     conflicts
    -0.62
     citation
    -0.59
     contradictions
    -0.58
     Authority
    -0.57
     stressing
    -0.57
     sectarian
    -0.56
    POSITIVE LOGITS
    athered
    1.33
    bsite
    1.28
    lder
    1.25
    arers
    1.20
    aving
    1.19
    asel
    1.19
    eding
    1.19
    avers
    1.17
    eps
    1.16
    eping
    1.15
    Activations Density 0.080%

    No Known Activations