© 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. 10-RES_POST_32K-OAI
    11. 29235
    Prev
    Next
    INDEX
    Explanations

    references to age and demographics in the context of individuals

    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
    +0.14
    0.6%
    573
    +0.13
    0.6%
    101
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.14
    0.04
    766
    +0.13
    0.03
    573
    +0.13
    0.02
    Negative Logits
    haven
    -0.69
    tackle
    -0.63
    SPONSORED
    -0.61
     reservation
    -0.57
    ikan
    -0.57
    inker
    -0.55
    onne
    -0.55
    anyon
    -0.55
     Horizon
    -0.55
     Sear
    -0.54
    POSITIVE LOGITS
     twenties
    1.36
     sevent
    1.06
     teens
    1.03
     late
    1.02
     mid
    0.94
    ixties
    0.93
     th
    0.91
     early
    0.89
     nin
    0.89
     40
    0.87
    Activations Density 0.309%

    No Known Activations