© 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. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4122
    Prev
    Next
    INDEX
    Explanations

    expressions of regret or missed opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    492
    +0.12
    0.5%
    445
    +0.09
    0.4%
    398
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.12
    0.01
    368
    +0.09
    0.01
    382
    +0.09
    0.01
    Negative Logits
    anooga
    -0.82
    renheit
    -0.81
    wx
    -0.80
    orio
    -0.78
    ername
    -0.76
    tyard
    -0.74
    aukee
    -0.73
    abwe
    -0.73
    lehem
    -0.72
    acia
    -0.71
    POSITIVE LOGITS
     Cosponsors
    0.69
     abolition
    0.62
     brakes
    0.62
     Ages
    0.61
     Yanuk
    0.61
    æĪ¦
    0.57
    20439
    0.57
     merits
    0.56
     eBook
    0.56
     empowering
    0.56
    Activations Density 0.062%

    No Known Activations