© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory 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
    759
    +0.10
    0.5%
    529
    +0.10
    0.4%
    313
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.08
    314
    +0.10
    -0.00
    232
    +0.09
    0.08
    Negative Logits
     ILCS
    -0.60
    enegger
    -0.55
    ufact
    -0.55
     Dragonbound
    -0.53
    etheless
    -0.53
     cracking
    -0.52
    INGTON
    -0.51
    é¾įå¥ij士
    -0.50
     CPC
    -0.50
    liners
    -0.50
    POSITIVE LOGITS
    a
    2.77
    aan
    1.36
    aa
    1.31
    aic
    1.25
    as
    1.20
    aaa
    1.19
    aah
    1.18
    ae
    1.16
    aaaa
    1.14
    ais
    1.10
    Activations Density 0.834%

    No Known Activations