© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26241
    Prev
    Next
    INDEX
    Explanations

    specific character patterns or sequences in text that indicate personal names or identifiers

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.13
    0.6%
    447
    +0.12
    0.5%
    295
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.09
    442
    +0.12
    0.09
    36
    +0.11
    0.08
    Negative Logits
     multim
    -0.78
     leg
    -0.73
     cort
    -0.72
     ident
    -0.72
     GSL
    -0.72
     unequ
    -0.71
     pc
    -0.71
     rectangle
    -0.70
     hors
    -0.70
     discrim
    -0.70
    POSITIVE LOGITS
    opol
    1.15
    opian
    1.13
    adan
    1.10
    ovsky
    1.08
    opia
    1.07
    ulhu
    1.07
    eca
    1.05
    agate
    1.04
    auts
    1.03
    aja
    1.03
    Activations Density 0.314%

    No Known Activations