© 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 EvalsExportsAPI 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. 28699
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named Carlos or Jose

    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
    538
    +0.12
    0.5%
    430
    +0.10
    0.5%
    698
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.05
    682
    +0.10
    0.03
    232
    +0.08
    0.04
    Negative Logits
    mble
    -0.94
    culosis
    -0.89
    etheus
    -0.82
    wcs
    -0.74
    atively
    -0.74
    iance
    -0.74
    ihar
    -0.71
    tsky
    -0.71
    ancies
    -0.70
    uity
    -0.70
    POSITIVE LOGITS
     Uri
    0.88
     Martinez
    0.86
     Gutierrez
    0.83
     Rivera
    0.79
     Rubio
    0.78
     Alberto
    0.78
     Lopez
    0.78
     Angel
    0.77
     Miranda
    0.77
     Enrique
    0.77
    Activations Density 0.332%

    No Known Activations