© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    names or identifiers associated with people or institutions

    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
    761
    +0.13
    0.6%
    399
    +0.10
    0.4%
    630
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.13
    0.03
    399
    +0.10
    0.03
    398
    +0.09
    0.03
    Negative Logits
    interstitial
    -0.76
    NAS
    -0.74
    ailability
    -0.68
     tyr
    -0.66
     challeng
    -0.65
     laun
    -0.63
    Marsh
    -0.63
     earthqu
    -0.62
    DEF
    -0.61
    wind
    -0.61
    POSITIVE LOGITS
    henko
    0.95
    naires
    0.68
    yan
    0.67
     bulls
    0.66
    ulo
    0.64
    oyal
    0.63
    zees
    0.63
    rophe
    0.61
    inoa
    0.61
    ateral
    0.61
    Activations Density 0.185%

    No Known Activations