© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37742
    Prev
    Next
    INDEX
    Explanations

    concepts related to duration or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.06
    2:0.10
    3:0.09
    4:0.08
    5:0.07
    6:0.08
    7:0.06
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
     seiz
    -1.74
    eeds
    -1.70
    affles
    -1.68
    terness
    -1.65
     ├
    -1.63
    aeda
    -1.62
    ffe
    -1.62
    -------
    -1.61
    paces
    -1.58
    --------------------
    -1.57
    POSITIVE LOGITS
     Stevenson
    1.66
     Macy
    1.55
     broadcaster
    1.54
     cryptoc
    1.52
    ��
    1.50
     Malone
    1.50
     lineback
    1.50
     telev
    1.45
    ��
    1.44
     Cull
    1.42
    Activations Density 0.000%

    No Known Activations