© 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. 27654
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" to indicate collective experiences or perspectives

    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
    314
    +0.24
    1.1%
    354
    +0.14
    0.6%
    624
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.24
    0.14
    551
    +0.14
    0.13
    718
    +0.11
    0.10
    Negative Logits
     sustainability
    -0.69
     DACA
    -0.68
     vis
    -0.67
     ESA
    -0.66
     deterrent
    -0.66
    âĢİ
    -0.64
     SYSTEM
    -0.61
     detriment
    -0.61
     Pathfinder
    -0.61
     MMR
    -0.60
    POSITIVE LOGITS
    eks
    1.13
    eds
    1.07
    ird
    1.02
    ights
    0.98
    aled
    0.97
    zzy
    0.97
    ighed
    0.96
    itsch
    0.95
    eer
    0.95
    eming
    0.94
    Activations Density 0.590%

    No Known Activations