© 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. 29853
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to documentation and citation

    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%
    379
    +0.12
    0.6%
    104
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.13
    0.01
    462
    +0.12
    0.02
    212
    +0.11
    0.01
    Negative Logits
    hal
    -0.86
    ï¸ı
    -0.82
    ãĤ¼
    -0.79
    ãĥ´ãĤ¡
    -0.77
    occ
    -0.72
    lot
    -0.70
    ãĥķãĤ©
    -0.70
     Alc
    -0.69
    ochet
    -0.68
    illac
    -0.66
    POSITIVE LOGITS
    BY
    1.12
    bys
    1.10
    by
    1.03
     BY
    1.00
     by
    0.90
     By
    0.89
    By
    0.84
    byn
    0.74
    ById
    0.73
    idity
    0.72
    Activations Density 0.690%

    No Known Activations