© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29472
    Prev
    Next
    INDEX
    Explanations

    references to individuals or characters with the name Ts or variations thereof

    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
    659
    +0.13
    0.6%
    402
    +0.12
    0.5%
    19
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.00
    103
    +0.12
    0.02
    489
    +0.10
    0.02
    Negative Logits
     mileage
    -0.86
    eering
    -0.69
    ãĥ¼ãĥĨ
    -0.68
     Machina
    -0.64
     Yankee
    -0.62
    theless
    -0.62
     JPM
    -0.61
     è£ıè
    -0.61
     NAS
    -0.60
     SAP
    -0.60
    POSITIVE LOGITS
    avorite
    1.33
    arnaev
    1.27
    ushima
    1.13
    arist
    1.08
    izoph
    0.97
    onga
    0.97
    cham
    0.94
    uda
    0.94
    ugi
    0.94
    ug
    0.94
    Activations Density 0.150%

    No Known Activations