© 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. 32612
    Prev
    Next
    INDEX
    Explanations

    details related to hurricanes, including their movements, intensities, and impacts

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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    574
    +0.11
    0.5%
    609
    +0.10
    0.5%
    192
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.11
    0.01
    260
    +0.10
    0.02
    655
    +0.10
    0.01
    Negative Logits
     chamber
    -0.74
    EStream
    -0.72
    hester
    -0.70
     Clarks
    -0.68
     corrid
    -0.67
     Spart
    -0.65
    apest
    -0.65
     sten
    -0.65
     abst
    -0.65
    zel
    -0.63
    POSITIVE LOGITS
     landfall
    0.97
     typh
    0.75
     Guam
    0.71
     hurricane
    0.69
    Japan
    0.67
    Dest
    0.67
     Japan
    0.66
    agic
    0.65
     Indonesian
    0.65
     unpop
    0.65
    Activations Density 0.032%

    No Known Activations