© 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. 4094
    Prev
    Next
    INDEX
    Explanations

    references to structural organization and categorization

    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
    720
    +0.13
    0.6%
    763
    +0.09
    0.4%
    483
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.13
    0.09
    89
    +0.09
    0.08
    383
    +0.09
    0.07
    Negative Logits
    avier
    -0.66
    ses
    -0.63
    istor
    -0.62
     catalyst
    -0.61
    luster
    -0.60
    .?
    -0.60
    sed
    -0.59
    issors
    -0.59
    anie
    -0.57
     Cinderella
    -0.57
    POSITIVE LOGITS
    £ı
    0.82
    pload
    0.78
    ãĤ·ãĥ£
    0.73
    undle
    0.72
    pmwiki
    0.67
    uckland
    0.66
    icho
    0.65
    ¬¼
    0.64
    amazon
    0.63
    é¾įå
    0.63
    Activations Density 4.186%

    No Known Activations