© 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. 28498
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological products and their features

    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
    640
    +0.13
    0.6%
    373
    +0.13
    0.6%
    486
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.03
    442
    +0.13
    0.03
    107
    +0.09
    0.03
    Negative Logits
    SPONSORED
    -0.89
    Interstitial
    -0.87
    pees
    -0.73
    ADVERTISEMENT
    -0.73
    hower
    -0.71
     Paste
    -0.70
    andom
    -0.66
     charact
    -0.66
    ought
    -0.65
    oÄŁ
    -0.65
    POSITIVE LOGITS
    inav
    0.71
    «ĺ
    0.57
     Mesa
    0.57
     AMD
    0.57
    meat
    0.56
     NVIDIA
    0.56
    inas
    0.55
     Intel
    0.55
    Fed
    0.55
     flaw
    0.54
    Activations Density 0.083%

    No Known Activations