© 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. 20136
    Prev
    Next
    INDEX
    Explanations

    references to beliefs and actions based on religious dictation

    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
    756
    +0.17
    0.8%
    567
    +0.10
    0.5%
    227
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.17
    -0.01
    351
    +0.10
    0.04
    567
    +0.10
    0.04
    Negative Logits
    ibaba
    -0.82
    Luck
    -0.82
    DragonMagazine
    -0.73
    antha
    -0.73
    uin
    -0.72
    catentry
    -0.71
    quick
    -0.71
     Pwr
    -0.70
     Rao
    -0.70
    arbon
    -0.70
    POSITIVE LOGITS
     morally
    1.14
     discriminating
    1.10
     coerc
    1.09
     discrim
    1.07
     discrimination
    1.06
     discriminatory
    1.05
     bigotry
    1.04
     bigot
    1.02
     derog
    1.01
     discriminate
    1.01
    Activations Density 1.016%

    No Known Activations