© 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. 26846
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and locations

    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
    393
    +0.12
    0.6%
    482
    +0.09
    0.4%
    46
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.08
    477
    +0.09
    0.05
    563
    +0.09
    0.07
    Negative Logits
    mble
    -0.63
    entry
    -0.62
    category
    -0.62
    erial
    -0.59
    edition
    -0.58
    aughtered
    -0.58
    dozen
    -0.58
    ertation
    -0.57
    AMD
    -0.56
    使
    -0.56
    POSITIVE LOGITS
     himself
    1.41
    's
    1.19
     herself
    1.09
     Himself
    0.98
     Productions
    0.92
     Industries
    0.90
     Enterprises
    0.89
     Sr
    0.87
     Jr
    0.79
     admits
    0.75
    Activations Density 0.762%

    No Known Activations