© 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. 27633
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and their formatting in various contexts

    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
    +0.13
    0.6%
    117
    +0.12
    0.6%
    525
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.05
    426
    +0.12
    0.04
    352
    +0.10
    0.05
    Negative Logits
    ooth
    -0.62
    ffen
    -0.62
    sten
    -0.58
    rox
    -0.58
     Borders
    -0.57
    yx
    -0.57
    ensitive
    -0.57
    ipper
    -0.55
    ï¸ı
    -0.55
    ograph
    -0.55
    POSITIVE LOGITS
    577
    0.83
    322
    0.82
    429
    0.80
    438
    0.79
    328
    0.78
    gage
    0.76
    148
    0.76
    341
    0.75
    331
    0.74
    143
    0.74
    Activations Density 0.202%

    No Known Activations