© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 32095
    Prev
    Next
    INDEX
    Explanations

    references to religious themes and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.5%
    193
    +0.10
    0.5%
    457
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.12
    0.16
    426
    +0.10
    0.11
    23
    +0.09
    0.13
    Negative Logits
    obbies
    -0.71
     bikes
    -0.71
     sponsoring
    -0.70
     planner
    -0.70
     skate
    -0.69
     fuzz
    -0.69
     fisheries
    -0.68
     briefs
    -0.68
     modelling
    -0.67
    chnology
    -0.67
    POSITIVE LOGITS
     Amen
    1.45
     Psal
    1.44
     Quran
    1.20
     Verse
    1.13
     ESV
    1.13
    Isa
    1.11
     Isaiah
    1.09
     verse
    1.07
     Hail
    1.03
    yrics
    1.00
    Activations Density 1.743%

    No Known Activations