© 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. 30823
    Prev
    Next
    INDEX
    Explanations

    references to roles or positions within a hierarchical structure or organization

    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
    308
    +0.17
    0.8%
    224
    +0.14
    0.6%
    114
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.17
    0.13
    537
    +0.14
    0.10
    114
    +0.09
    0.09
    Negative Logits
    xual
    -0.75
    cffffcc
    -0.72
    ursed
    -0.70
    opath
    -0.68
    izontal
    -0.67
    strument
    -0.66
     inhibitors
    -0.66
    illance
    -0.66
    obi
    -0.66
    osphere
    -0.65
    POSITIVE LOGITS
     Jonah
    1.06
     Quentin
    1.06
     Darrell
    1.05
     Greg
    1.05
     Colin
    1.04
     Axel
    1.03
     Charles
    1.03
     Sidney
    1.03
     Alan
    1.03
     Gian
    1.02
    Activations Density 0.967%

    No Known Activations