© 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. 28238
    Prev
    Next
    INDEX
    Explanations

    references to teams and team-related terminology

    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
    476
    +0.12
    0.6%
    669
    +0.12
    0.5%
    197
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.02
    508
    +0.12
    0.01
    314
    +0.11
    -0.01
    Negative Logits
    ensional
    -0.85
    Ö¼
    -0.81
    answer
    -0.78
    redo
    -0.72
    umerable
    -0.72
    itol
    -0.71
    matter
    -0.69
     Zeit
    -0.68
    romy
    -0.63
    axter
    -0.62
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.70
     Tycoon
    0.69
    NECT
    0.67
     discharged
    0.58
    weeney
    0.57
    swick
    0.57
     Mines
    0.57
    unts
    0.57
     ABE
    0.57
    LS
    0.57
    Activations Density 0.236%

    No Known Activations