© 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. 26969
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and their frequency in text

    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
    639
    +0.10
    0.5%
    191
    +0.10
    0.5%
    652
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.11
    354
    +0.10
    0.09
    551
    +0.10
    0.08
    Negative Logits
    riched
    -0.78
    osate
    -0.78
    enhagen
    -0.69
    iasco
    -0.69
    quished
    -0.68
    ãĤ´ãĥ³
    -0.67
    ãĥ¼ãĤ¯
    -0.67
    76561
    -0.67
    bold
    -0.66
    èĢħ
    -0.65
    POSITIVE LOGITS
     asleep
    0.74
     Whats
    0.67
    'm
    0.65
     least
    0.64
    chy
    0.64
     wee
    0.64
     sleeps
    0.63
    sle
    0.63
    fare
    0.63
    're
    0.61
    Activations Density 0.581%

    No Known Activations