© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to people and 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
    682
    +0.12
    0.5%
    481
    +0.09
    0.4%
    27
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.12
    0.05
    473
    +0.09
    0.04
    239
    +0.09
    0.05
    Negative Logits
    senal
    -0.71
     basics
    -0.68
    abouts
    -0.66
     HQ
    -0.61
     oppression
    -0.60
     Mandatory
    -0.60
    paces
    -0.60
    ikuman
    -0.59
     Beats
    -0.59
     classroom
    -0.59
    POSITIVE LOGITS
    ilon
    0.73
    ño
    0.66
    ´
    0.65
    arlane
    0.64
    ange
    0.63
    ellar
    0.62
     incarn
    0.62
    ablo
    0.61
    án
    0.61
    lli
    0.60
    Activations Density 1.204%

    No Known Activations