© 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. 28001
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics and game scenarios

    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
    306
    +0.13
    0.6%
    153
    +0.12
    0.6%
    289
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    589
    +0.13
    0.04
    238
    +0.12
    0.04
    362
    +0.11
    0.06
    Negative Logits
    vernment
    -0.80
    tis
    -0.74
     impunity
    -0.72
    sonian
    -0.71
    DonaldTrump
    -0.67
    CRIP
    -0.64
    в
    -0.63
     infinity
    -0.63
    ~~~~~~~~~~~~~~~~
    -0.63
    hov
    -0.63
    POSITIVE LOGITS
     field
    0.79
    field
    0.77
    ilda
    0.71
     schedule
    0.69
    ahs
    0.67
    rate
    0.67
     measure
    0.65
     pack
    0.65
    ENSE
    0.64
    inant
    0.64
    Activations Density 0.612%

    No Known Activations