© 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. 4272
    Prev
    Next
    INDEX
    Explanations

    names and references related to specific individuals, mainly Russian and Ukrainian figures

    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
    291
    +0.12
    0.5%
    668
    +0.09
    0.4%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.05
    668
    +0.09
    0.04
    767
    +0.09
    0.03
    Negative Logits
     Robbins
    -0.86
     Sally
    -0.73
    iaries
    -0.72
     Betty
    -0.71
     reps
    -0.68
     juices
    -0.65
     Erica
    -0.64
    jury
    -0.63
     Daisy
    -0.63
    Jackson
    -0.63
    POSITIVE LOGITS
    kov
    1.17
    achev
    1.14
    ende
    0.98
    etsk
    0.93
    zbek
    0.92
    ansky
    0.92
    sov
    0.90
    imov
    0.87
    kaya
    0.86
    hran
    0.85
    Activations Density 0.519%

    No Known Activations