© 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. 27741
    Prev
    Next
    INDEX
    Explanations

    the article "the" and references to various subjects or topics indicated by the context

    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
    546
    +0.10
    0.5%
    539
    +0.09
    0.4%
    454
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.14
    393
    +0.09
    0.09
    385
    +0.09
    0.08
    Negative Logits
    enance
    -0.76
    conom
    -0.72
    ynski
    -0.70
    iHUD
    -0.65
    nai
    -0.62
    thood
    -0.61
    KY
    -0.60
    ettings
    -0.60
     outweigh
    -0.60
    Interstitial
    -0.59
    POSITIVE LOGITS
     hands
    0.92
     trash
    0.81
     wolves
    0.77
     desk
    0.77
     compost
    0.75
     printers
    0.75
     landfill
    0.74
     doorstep
    0.74
     chopping
    0.73
    flame
    0.72
    Activations Density 1.039%

    No Known Activations