© 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. 26285
    Prev
    Next
    INDEX
    Explanations

    occurrences of the city name "Los Angeles"

    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
    742
    +0.11
    0.5%
    483
    +0.10
    0.5%
    553
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.11
    0.03
    752
    +0.10
    0.03
    483
    +0.08
    0.02
    Negative Logits
    ãĤ¡
    -0.64
    ebook
    -0.61
    ternity
    -0.59
    BOOK
    -0.58
    ruary
    -0.56
    orsche
    -0.56
    oys
    -0.56
    orted
    -0.56
     chance
    -0.55
    FontSize
    -0.55
    POSITIVE LOGITS
     Angeles
    1.69
     Alam
    1.06
    Angel
    0.96
     Santos
    0.94
     ANGEL
    0.91
     Padres
    0.88
    angel
    0.87
     Blanc
    0.80
    er
    0.79
    ighter
    0.77
    Activations Density 0.083%

    No Known Activations