© 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. 6844
    Prev
    Next
    INDEX
    Explanations

    references to illness or medical conditions

    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
    655
    +0.11
    0.5%
    178
    +0.11
    0.5%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.11
    0.02
    655
    +0.11
    0.02
    285
    +0.09
    0.01
    Negative Logits
    âĹ¼
    -0.65
    EStreamFrame
    -0.63
    ourke
    -0.61
    EStream
    -0.57
    SPONSORED
    -0.57
    phrine
    -0.56
     Freeze
    -0.55
     Sapp
    -0.54
     Pione
    -0.54
     Citation
    -0.54
    POSITIVE LOGITS
    uminati
    1.45
    ogical
    1.27
    iberal
    1.21
    umin
    1.17
    iquid
    1.16
    usive
    1.10
    awar
    1.09
    inois
    1.05
    usional
    0.90
    icit
    0.87
    Activations Density 0.023%

    No Known Activations