© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4337
    Prev
    Next
    INDEX
    Explanations

    instances where "take" is used in a context suggesting examples or illustrations

    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
    497
    +0.17
    0.8%
    52
    +0.13
    0.6%
    227
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.17
    0.07
    48
    +0.13
    0.07
    52
    +0.13
    0.08
    Negative Logits
    humans
    -0.74
    ysc
    -0.72
     Forced
    -0.68
    ixtape
    -0.67
    ossier
    -0.67
    othal
    -0.66
    cosystem
    -0.66
    "))
    -0.66
     Written
    -0.65
     Cards
    -0.64
    POSITIVE LOGITS
    Ô
    0.67
    :,
    0.65
     yourselves
    0.65
    *:
    0.63
    }{
    0.62
     ming
    0.61
     Whitman
    0.60
    :]
    0.60
    _{
    0.58
     embod
    0.58
    Activations Density 4.838%

    No Known Activations