© 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. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4153
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to programming concepts and structures

    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
    373
    +0.16
    0.7%
    716
    +0.11
    0.5%
    193
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.16
    0.02
    640
    +0.11
    0.03
    747
    +0.11
    0.02
    Negative Logits
    ITE
    -0.70
     pastoral
    -0.68
    Bone
    -0.66
    TOP
    -0.61
    ãĥ»
    -0.61
     chipset
    -0.60
    ForgeModLoader
    -0.59
    UA
    -0.58
    Armor
    -0.58
    existent
    -0.57
    POSITIVE LOGITS
    ï¸
    0.79
     Janeiro
    0.73
    olulu
    0.72
    ichick
    0.71
    ependence
    0.69
    glers
    0.69
     vag
    0.67
    othal
    0.64
    identally
    0.64
    assetsadobe
    0.62
    Activations Density 0.258%

    No Known Activations