© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical analysis-related terms

    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
    430
    +0.16
    0.7%
    356
    +0.12
    0.6%
    616
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.16
    0.12
    464
    +0.12
    0.07
    480
    +0.09
    0.07
    Negative Logits
    ongyang
    -0.93
    orno
    -0.79
    chwitz
    -0.77
    stals
    -0.77
    acons
    -0.74
    conserv
    -0.72
    wcs
    -0.68
    adata
    -0.68
    ilon
    -0.68
    ixon
    -0.67
    POSITIVE LOGITS
     SECTION
    0.71
    zan
    0.66
     Forth
    0.66
     COUR
    0.60
    iHUD
    0.57
     Kens
    0.57
     Published
    0.57
     ].
    0.56
     Ryu
    0.56
     RELE
    0.55
    Activations Density 2.170%

    No Known Activations