© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27644
    Prev
    Next
    INDEX
    Explanations

    numerical representations of measurements and weights

    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
    207
    +0.10
    0.4%
    666
    +0.10
    0.4%
    418
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.05
    678
    +0.10
    0.04
    537
    +0.09
    0.04
    Negative Logits
     Scores
    -0.83
     scores
    -0.70
     Annotations
    -0.68
     ruins
    -0.67
     fuck
    -0.65
     averages
    -0.65
     Mayo
    -0.64
     dads
    -0.64
     dinners
    -0.64
     underdog
    -0.64
    POSITIVE LOGITS
    cyl
    1.07
    layer
    1.03
    ply
    1.01
    position
    1.01
    val
    1.00
    amp
    0.99
    slot
    0.99
    cell
    0.97
    mill
    0.97
    bolt
    0.96
    Activations Density 0.312%

    No Known Activations