© 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. 26720
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and their associated contexts

    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
    +0.14
    0.7%
    237
    +0.11
    0.5%
    756
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.14
    0.04
    683
    +0.11
    0.05
    449
    +0.11
    0.04
    Negative Logits
    ibal
    -0.70
    query
    -0.69
    efe
    -0.67
    arij
    -0.65
    chid
    -0.62
    taboola
    -0.62
    factor
    -0.61
    ktop
    -0.61
    è¦
    -0.61
    xtap
    -0.61
    POSITIVE LOGITS
     stories
    0.94
     everything
    0.93
     goodbye
    0.93
     plainly
    0.92
     bluntly
    0.92
     hello
    0.85
     tales
    0.85
     otherwise
    0.83
     nothing
    0.82
     beforehand
    0.80
    Activations Density 0.164%

    No Known Activations