© 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. 27995
    Prev
    Next
    INDEX
    Explanations

    references to events and elements related to the Olympics

    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
    118
    +0.11
    0.5%
    97
    +0.10
    0.4%
    646
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    650
    +0.11
    0.10
    97
    +0.10
    0.01
    86
    +0.09
    0.07
    Negative Logits
     Ezra
    -0.88
     Rye
    -0.80
     Sparrow
    -0.80
     Dickinson
    -0.79
    Dispatch
    -0.79
     Cousins
    -0.79
    ebted
    -0.79
     Dispatch
    -0.78
     Mercer
    -0.76
     Tucker
    -0.75
    POSITIVE LOGITS
     IOC
    2.00
     athletes
    1.88
     Athlet
    1.88
     Olympic
    1.88
     doping
    1.85
     Olympics
    1.72
     athlete
    1.67
     Paraly
    1.58
     athletics
    1.58
     Olymp
    1.57
    Activations Density 6.216%

    No Known Activations