© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    key terms related to scientific investigations and technologies

    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
    459
    +0.19
    0.9%
    745
    +0.13
    0.6%
    46
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.19
    0.09
    225
    +0.13
    0.13
    447
    +0.12
    0.21
    Negative Logits
     mole
    -0.64
     psychiatrists
    -0.62
    Controller
    -0.62
     psychiatrist
    -0.61
    Generic
    -0.60
     Gle
    -0.59
     Jace
    -0.59
     qual
    -0.58
    MpServer
    -0.58
     Tsu
    -0.57
    POSITIVE LOGITS
    indal
    0.85
    ardless
    0.82
    hammad
    0.80
    anu
    0.79
    arsity
    0.77
    anus
    0.75
    chnology
    0.73
    inous
    0.72
    ylon
    0.71
    upe
    0.69
    Activations Density 10.594%

    No Known Activations