© 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. 30978
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated relationships

    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
    314
    +0.16
    0.7%
    295
    +0.10
    0.5%
    282
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.16
    -0.01
    406
    +0.10
    0.05
    675
    +0.09
    0.05
    Negative Logits
     Languages
    -0.82
     fronts
    -0.78
     Categories
    -0.74
     behavi
    -0.74
     Closing
    -0.73
     Menu
    -0.71
     Quote
    -0.70
     Emails
    -0.68
     ðŁij
    -0.67
     scripts
    -0.65
    POSITIVE LOGITS
    76561
    1.01
    ãĥ´ãĤ¡
    0.94
    270
    0.88
    ãģ®éŃĶ
    0.88
    ELY
    0.86
     698
    0.85
    REDACTED
    0.81
    471
    0.80
    reed
    0.79
    bh
    0.78
    Activations Density 0.483%

    No Known Activations