© 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. 8-RES_POST_32K-OAI
    11. 9106
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verbs "have" and "had" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    190
    +0.09
    0.4%
    752
    +0.09
    0.4%
    441
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.09
    0.07
    282
    +0.09
    0.07
    7
    +0.09
    0.06
    Negative Logits
    Reviewer
    -0.76
     Fiorina
    -0.62
     ridden
    -0.62
     Typh
    -0.62
     Fortune
    -0.61
     overrun
    -0.61
     condem
    -0.59
    ustomed
    -0.59
    RNA
    -0.59
     staffed
    -0.57
    POSITIVE LOGITS
     ramifications
    1.01
     consequences
    1.01
     implications
    0.98
     repercussions
    0.95
    roots
    0.81
     implication
    0.80
     ripple
    0.80
     significance
    0.79
     unintended
    0.79
     reperc
    0.78
    Activations Density 0.326%

    No Known Activations