© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29537
    Prev
    Next
    INDEX
    Explanations

    instances of quantitative data and statistics

    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
    350
    +0.11
    0.5%
    316
    +0.11
    0.5%
    297
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.16
    608
    +0.11
    0.14
    393
    +0.10
    0.10
    Negative Logits
    sonian
    -0.76
    umbn
    -0.70
    udic
    -0.70
     Canaver
    -0.70
    bol
    -0.68
     indo
    -0.64
    tnc
    -0.62
    olit
    -0.60
    reet
    -0.60
     Wast
    -0.60
    POSITIVE LOGITS
     percentage
    1.65
     proportion
    1.53
    Percent
    1.45
     ratio
    1.43
     percentages
    1.39
     median
    1.39
     average
    1.38
    percent
    1.33
    Average
    1.32
     rate
    1.31
    Activations Density 0.829%

    No Known Activations