© 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. 26324
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places

    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
    35
    +0.13
    0.6%
    230
    +0.11
    0.5%
    636
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.05
    288
    +0.11
    0.05
    232
    +0.11
    0.04
    Negative Logits
    ers
    -0.78
    eport
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.67
    ¬¼
    -0.64
    erers
    -0.63
     targ
    -0.62
    ist
    -0.61
     Glac
    -0.61
    ioxide
    -0.61
    ering
    -0.60
    POSITIVE LOGITS
    pin
    0.86
    tan
    0.85
    nan
    0.84
    forth
    0.82
    vous
    0.80
    cart
    0.79
    dale
    0.79
    gan
    0.77
    gil
    0.77
    by
    0.76
    Activations Density 0.304%

    No Known Activations