© 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. 26806
    Prev
    Next
    INDEX
    Explanations

    terms related to religion and its various aspects

    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
    546
    +0.10
    0.5%
    288
    +0.10
    0.5%
    351
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.04
    461
    +0.10
    0.03
    351
    +0.10
    0.03
    Negative Logits
    kus
    -1.01
    hyde
    -0.80
    ptives
    -0.73
     Lans
    -0.71
    ription
    -0.71
    ilage
    -0.70
    isode
    -0.69
    ilus
    -0.68
    hap
    -0.67
    amaz
    -0.66
    POSITIVE LOGITS
    ophobia
    0.99
    ophobic
    0.94
     affiliation
    0.94
     affili
    0.89
     tenets
    0.87
     worshipped
    0.85
    ophob
    0.82
     scriptures
    0.81
     teaches
    0.81
     fundamentalist
    0.79
    Activations Density 0.110%

    No Known Activations