© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    references to Texas A&M University

    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
    229
    +0.10
    0.4%
    71
    +0.10
    0.4%
    322
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.10
    0.01
    583
    +0.10
    0.01
    322
    +0.09
    0.01
    Negative Logits
    opian
    -0.79
     equilibrium
    -0.69
    alore
    -0.68
     stranded
    -0.68
    istant
    -0.67
    oxide
    -0.67
    etheus
    -0.66
     immunity
    -0.66
    agine
    -0.64
    agon
    -0.64
    POSITIVE LOGITS
    ï¸
    0.70
     Reincarn
    0.68
    è¦ļéĨĴ
    0.67
    Spons
    0.67
     Pix
    0.66
     Regulations
    0.66
     Crimes
    0.65
    MSN
    0.64
    ngth
    0.63
    CLE
    0.63
    Activations Density 0.082%

    No Known Activations