© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29370
    Prev
    Next
    INDEX
    Explanations

    references to historical timelines and events related to publications and the evolution of concepts

    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
    405
    +0.13
    0.6%
    252
    +0.11
    0.5%
    177
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.13
    0.18
    724
    +0.11
    0.21
    540
    +0.10
    0.17
    Negative Logits
     theirs
    -0.85
     THEIR
    -0.75
     their
    -0.73
    their
    -0.70
     goodies
    -0.68
     THEY
    -0.65
    edo
    -0.60
    ibles
    -0.60
    Their
    -0.60
    allery
    -0.59
    POSITIVE LOGITS
    among
    0.86
     among
    0.80
     globally
    0.78
     nationally
    0.78
    itatively
    0.77
     internationally
    0.74
     nationwide
    0.73
     universally
    0.72
     widely
    0.72
     Worldwide
    0.71
    Activations Density 4.066%

    No Known Activations