© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    action verbs related to physical activities and tasks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    65
    +0.11
    0.5%
    372
    +0.09
    0.4%
    184
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.10
    184
    +0.09
    0.05
    59
    +0.09
    0.06
    Negative Logits
    lihood
    -0.86
     opting
    -0.74
    akening
    -0.72
     oblig
    -0.71
     specifying
    -0.68
    endif
    -0.68
     asserting
    -0.67
    else
    -0.64
    Already
    -0.64
     integrating
    -0.64
    POSITIVE LOGITS
     knives
    1.03
     baskets
    0.94
     nails
    0.93
     plates
    0.92
     vegetables
    0.91
     tomatoes
    0.90
     pies
    0.90
     carrots
    0.89
     balloons
    0.88
     roses
    0.87
    Activations Density 1.119%

    No Known Activations