© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5085
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities related to the clergy or religious organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    137
    +0.14
    0.6%
    285
    +0.10
    0.5%
    106
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.14
    0.03
    588
    +0.10
    0.03
    106
    +0.10
    0.04
    Negative Logits
    ãĤ®
    -0.74
    κ
    -0.70
     caution
    -0.67
    hered
    -0.65
    fal
    -0.64
    ki
    -0.64
    tale
    -0.64
    ï¸
    -0.64
    sov
    -0.63
    gers
    -0.63
    POSITIVE LOGITS
    oser
    1.04
    osing
    0.98
    INTON
    0.96
    avier
    0.96
    OSED
    0.95
    ueless
    0.93
    uster
    0.93
    amps
    0.92
    opez
    0.92
    aughlin
    0.90
    Activations Density 0.056%

    No Known Activations