© 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. 26864
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "United" in various 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
    288
    +0.11
    0.5%
    175
    +0.10
    0.5%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.11
    0.03
    677
    +0.10
    0.04
    232
    +0.10
    0.04
    Negative Logits
    phrine
    -0.75
    uble
    -0.66
    tnc
    -0.66
    ï¸ı
    -0.66
    pit
    -0.64
    bryce
    -0.63
    bard
    -0.63
    ãĤ¼
    -0.62
    ouf
    -0.62
    eworks
    -0.61
    POSITIVE LOGITS
     States
    1.25
     Nations
    1.15
     Methodist
    1.09
    States
    0.98
     Airlines
    0.94
    sburg
    0.89
     Kingdom
    0.88
     STATES
    0.83
    Health
    0.83
     Shades
    0.79
    Activations Density 0.320%

    No Known Activations