© 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. 3709
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotional or physical reactions to situations

    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
    669
    +0.10
    0.5%
    234
    +0.10
    0.5%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.07
    669
    +0.10
    0.04
    398
    +0.10
    0.05
    Negative Logits
    soDeliveryDate
    -0.79
    isSpecialOrderable
    -0.78
    ItemThumbnailImage
    -0.77
    pit
    -0.72
    ports
    -0.70
    OTOS
    -0.69
     aliases
    -0.69
    ãĥİ
    -0.69
    Rust
    -0.68
    wcsstore
    -0.68
    POSITIVE LOGITS
    essage
    0.86
    laim
    0.85
    ocrat
    0.80
    ciating
    0.77
    ebook
    0.76
    ocracy
    0.74
    ocr
    0.73
    fy
    0.69
    utic
    0.66
    cius
    0.66
    Activations Density 1.517%

    No Known Activations