© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    words associated with tasting and food-related experiences

    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
    391
    +0.11
    0.5%
    329
    +0.11
    0.5%
    367
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.11
    0.02
    415
    +0.11
    0.02
    367
    +0.10
    0.02
    Negative Logits
    maxwell
    -0.74
    enegger
    -0.74
    quarters
    -0.68
    ĨĴ
    -0.62
     Sundays
    -0.61
    ften
    -0.60
     GOT
    -0.59
     USE
    -0.59
     horr
    -0.57
    duino
    -0.56
    POSITIVE LOGITS
    opal
    0.81
    idated
    0.78
     Sands
    0.75
    oise
    0.74
    uala
    0.73
    à¥
    0.71
    Recommend
    0.71
     Vit
    0.70
    ovo
    0.67
    oso
    0.66
    Activations Density 0.051%

    No Known Activations