© 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. 32760
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements

    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%
    131
    +0.09
    0.4%
    166
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.13
    0.05
    305
    +0.09
    0.05
    731
    +0.09
    0.02
    Negative Logits
     Gems
    -0.79
     gems
    -0.69
     Machines
    -0.68
     Lust
    -0.66
     Seen
    -0.66
    locks
    -0.66
     Seeds
    -0.65
    Documents
    -0.65
     Cases
    -0.64
     GEAR
    -0.64
    POSITIVE LOGITS
     gallon
    0.87
     marathon
    0.80
    iversary
    0.76
     millennial
    0.75
    ottest
    0.75
    itarian
    0.73
    interstitial
    0.72
     multi
    0.72
    shapeshifter
    0.72
    yssey
    0.71
    Activations Density 1.213%

    No Known Activations