© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14208
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual references, particularly related to Christianity

    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
    350
    +0.15
    0.7%
    443
    +0.09
    0.4%
    210
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.15
    0.03
    210
    +0.09
    0.02
    25
    +0.09
    0.02
    Negative Logits
    Els
    -0.81
    Beer
    -0.78
    ockey
    -0.75
    ãĤ¤ãĥĪ
    -0.71
    OPA
    -0.70
    */(
    -0.70
     pubs
    -0.70
    pmwiki
    -0.68
    ãĥĵ
    -0.68
    ãĥķãĤ¡
    -0.66
    POSITIVE LOGITS
     Himself
    1.32
     Incarn
    1.18
     Almighty
    1.16
     Jesus
    1.07
     Messiah
    1.06
     Apostles
    1.06
    iour
    1.06
     Apostle
    1.01
     Creator
    1.01
     redeemed
    1.00
    Activations Density 0.064%

    No Known Activations