© 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. 3157
    Prev
    Next
    INDEX
    Explanations

    numerical values and data points

    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
    609
    +0.14
    0.7%
    225
    +0.11
    0.5%
    464
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.14
    0.04
    153
    +0.11
    0.04
    464
    +0.10
    0.03
    Negative Logits
     nep
    -0.77
     swelling
    -0.75
    attach
    -0.73
     metic
    -0.70
     disemb
    -0.70
    ring
    -0.69
     livest
    -0.68
     artif
    -0.67
    amen
    -0.67
    rings
    -0.67
    POSITIVE LOGITS
     Duffy
    0.71
    payers
    0.67
     taxpayers
    0.66
     kcal
    0.66
    å§«
    0.64
    士
    0.62
    vre
    0.60
    YR
    0.59
    uristic
    0.59
     Jacobs
    0.58
    Activations Density 0.524%

    No Known Activations