© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    mentions of Google and its various products or acquisitions

    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
    379
    +0.10
    0.5%
    159
    +0.10
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.10
    0.07
    352
    +0.10
    0.06
    317
    +0.10
    0.06
    Negative Logits
    ract
    -0.81
    lace
    -0.77
    nants
    -0.76
    arat
    -0.73
    unct
    -0.72
    sequence
    -0.71
    igmat
    -0.71
    idences
    -0.69
     Sabb
    -0.69
    ridden
    -0.69
    POSITIVE LOGITS
    ONSORED
    0.81
    SON
    0.72
     NEWS
    0.70
     marketing
    0.70
     exec
    0.69
    ENN
    0.69
     logo
    0.68
     Motorsport
    0.67
     fan
    0.67
     advertis
    0.67
    Activations Density 1.196%

    No Known Activations