© 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. 28729
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "U.S." and variations of it

    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
    305
    +0.12
    0.5%
    667
    +0.11
    0.5%
    8
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.06
    699
    +0.11
    0.04
    113
    +0.10
    0.04
    Negative Logits
    soever
    -0.76
    aviour
    -0.68
    \/\/
    -0.68
    advertisement
    -0.66
    selves
    -0.62
    adult
    -0.62
    ãĢİ
    -0.61
    à¼
    -0.61
     exclusive
    -0.60
    rones
    -0.60
    POSITIVE LOGITS
    wat
    0.79
    Conn
    0.76
     Michaels
    0.73
     Rollins
    0.69
    roots
    0.68
    worth
    0.68
    yers
    0.67
     Angelo
    0.65
    tz
    0.64
     Suffolk
    0.64
    Activations Density 0.464%

    No Known Activations