© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    key historical figures and significant events related to governance and societal issues

    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
    663
    +0.12
    0.5%
    126
    +0.10
    0.5%
    450
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    663
    +0.12
    0.08
    511
    +0.10
    0.11
    391
    +0.09
    0.06
    Negative Logits
    Jere
    -0.77
    irlf
    -0.71
    rily
    -0.67
    âĺ
    -0.66
    widget
    -0.63
    usercontent
    -0.63
     msec
    -0.58
    dragon
    -0.58
    nil
    -0.58
     elim
    -0.57
    POSITIVE LOGITS
     Cause
    0.69
    ãĤ¼ãĤ¦ãĤ¹
    0.65
    alogy
    0.63
     Prim
    0.62
    ¶
    0.61
     Distribution
    0.60
    ulative
    0.60
    uctions
    0.59
     varied
    0.59
    inar
    0.58
    Activations Density 2.638%

    No Known Activations