© 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. 26362
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future expectations or predictions

    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
    106
    +0.12
    0.5%
    490
    +0.10
    0.5%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.12
    0.03
    8
    +0.10
    0.03
    38
    +0.10
    0.02
    Negative Logits
    rehens
    -0.69
     PhD
    -0.64
    natureconservancy
    -0.64
     Telescope
    -0.62
     Leviathan
    -0.62
     IPM
    -0.60
    orno
    -0.56
     somet
    -0.55
     Habit
    -0.55
    government
    -0.55
    POSITIVE LOGITS
    ly
    0.77
    ãĥł
    0.75
    edIn
    0.71
    ached
    0.70
    ologically
    0.67
    unct
    0.66
    ainer
    0.66
    ained
    0.66
    aneous
    0.65
    ered
    0.65
    Activations Density 0.186%

    No Known Activations