© 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. 27015
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people

    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
    373
    +0.13
    0.6%
    8
    +0.10
    0.5%
    426
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.09
    314
    +0.10
    -0.00
    503
    +0.10
    0.02
    Negative Logits
    ãĤ´ãĥ³
    -0.74
    ĸļ
    -0.72
     Dill
    -0.68
     Lesbian
    -0.68
    ģĸ
    -0.66
     Kel
    -0.65
     Kali
    -0.65
     Ples
    -0.64
     Doodle
    -0.64
    ignty
    -0.64
    POSITIVE LOGITS
    gewater
    0.58
    Princ
    0.55
    Ca
    0.53
    Way
    0.53
    dinand
    0.52
    —-
    0.52
    Great
    0.52
    berman
    0.51
    Strange
    0.51
    win
    0.51
    Activations Density 1.011%

    No Known Activations