© 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. 28778
    Prev
    Next
    INDEX
    Explanations

    terms related to limitless quantities or frequencies

    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
    237
    +0.13
    0.6%
    308
    +0.10
    0.4%
    574
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    585
    +0.13
    0.02
    222
    +0.10
    0.02
    237
    +0.10
    0.01
    Negative Logits
    ective
    -0.93
    acus
    -0.90
    bourg
    -0.82
    iquette
    -0.81
    Reviewed
    -0.80
    oyal
    -0.76
    */(
    -0.71
    ector
    -0.71
    Downloadha
    -0.70
    avid
    -0.70
    POSITIVE LOGITS
     regress
    1.18
     amounts
    0.99
     amount
    0.98
     possibilities
    0.97
     Tsukuyomi
    0.96
     supply
    0.90
     loop
    0.90
     loops
    0.86
     quantities
    0.83
     number
    0.82
    Activations Density 0.160%

    No Known Activations