© 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. 30630
    Prev
    Next
    INDEX
    Explanations

    tokens that appear to represent numerical values or identifiers

    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
    +0.17
    0.8%
    454
    +0.11
    0.5%
    217
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.17
    -0.01
    316
    +0.11
    0.01
    284
    +0.10
    0.01
    Negative Logits
    pmwiki
    -1.00
    cffff
    -0.92
    href
    -0.84
    eln
    -0.84
    dfx
    -0.79
    efe
    -0.77
    yip
    -0.76
    rowd
    -0.76
    xus
    -0.75
    ewitness
    -0.74
    POSITIVE LOGITS
     Unc
    0.67
     Disorders
    0.65
     Rear
    0.64
     Dis
    0.61
     Low
    0.60
     Full
    0.60
     Split
    0.59
     sho
    0.58
     Tycoon
    0.58
     False
    0.58
    Activations Density 0.061%

    No Known Activations