© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3888
    Prev
    Next
    INDEX
    Explanations

    numerical data related to percentages and statistics

    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
    334
    +0.11
    0.5%
    177
    +0.11
    0.5%
    196
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.11
    0.03
    177
    +0.11
    0.02
    522
    +0.10
    0.02
    Negative Logits
     aloud
    -0.69
    ...?
    -0.68
    Jere
    -0.66
     disapp
    -0.66
     fulfilled
    -0.65
    minist
    -0.63
    ANN
    -0.63
    plays
    -0.61
    ronic
    -0.61
    Jud
    -0.60
    POSITIVE LOGITS
     backdrop
    0.69
    /)
    0.65
    iral
    0.64
    ï¸ı
    0.64
     Senegal
    0.62
    ãĤ¹
    0.62
    Enlarge
    0.62
    entin
    0.61
     Frenchman
    0.60
     ISBN
    0.60
    Activations Density 0.211%

    No Known Activations