© 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. 4555
    Prev
    Next
    INDEX
    Explanations

    phrases related to websites and online platforms

    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
    766
    +0.10
    0.5%
    496
    +0.10
    0.5%
    171
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.10
    0.05
    767
    +0.10
    0.04
    409
    +0.09
    0.04
    Negative Logits
    ©¶æ
    -0.78
     Fulton
    -0.67
     Eighth
    -0.67
    itone
    -0.66
     Xi
    -0.66
     inspectors
    -0.66
     Ninth
    -0.64
     Fitzgerald
    -0.63
    )=(
    -0.63
     Rafael
    -0.62
    POSITIVE LOGITS
    kr
    0.92
    ucks
    0.86
    estead
    0.80
    podcast
    0.79
    dp
    0.78
    mind
    0.77
    quest
    0.77
    yp
    0.77
    Examples
    0.74
    gp
    0.74
    Activations Density 2.191%

    No Known Activations