© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    titles or roles associated with deputy positions in various organizations

    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
    542
    +0.11
    0.5%
    314
    +0.10
    0.5%
    360
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.11
    0.02
    314
    +0.10
    0.02
    328
    +0.10
    0.02
    Negative Logits
    olini
    -0.70
    erella
    -0.65
     cringe
    -0.62
     Quadro
    -0.62
     firsthand
    -0.60
     smile
    -0.60
     Egyptians
    -0.59
    iversary
    -0.59
     barbecue
    -0.59
    ophobia
    -0.58
    POSITIVE LOGITS
    Domin
    0.78
    uties
    0.72
    argo
    0.70
    à¨
    0.68
    Contents
    0.68
    catentry
    0.68
    xit
    0.67
    Accessory
    0.66
    arters
    0.65
    leases
    0.65
    Activations Density 0.230%

    No Known Activations