© 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. 30883
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing contrasting ideas or comparisons

    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
    373
    +0.13
    0.6%
    617
    +0.10
    0.5%
    519
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.05
    489
    +0.10
    0.03
    562
    +0.09
    0.03
    Negative Logits
    ãĥIJ
    -0.66
    lake
    -0.65
    rats
    -0.64
    bugs
    -0.62
    bourg
    -0.60
    furt
    -0.58
    Fal
    -0.57
    laws
    -0.57
    å¼
    -0.56
    kus
    -0.55
    POSITIVE LOGITS
     plus
    1.07
     upside
    1.04
     contrary
    0.97
     brighter
    0.89
     bright
    0.88
     flip
    0.87
    ï¸
    0.78
     surface
    0.77
     downside
    0.75
     whole
    0.75
    Activations Density 0.285%

    No Known Activations