© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21263
    Prev
    Next
    INDEX
    Explanations

    significant numerical values and time references in relation to events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.03
    5:0.21
    6:0.02
    7:0.03
    8:0.02
    9:0.44
    10:0.02
    11:0.07
    Negative Logits
     principally
    -2.54
    onymous
    -2.38
     universally
    -2.16
    ographed
    -2.15
     unlawfully
    -2.13
     criminally
    -2.12
     egreg
    -2.11
     prominently
    -2.09
    DERR
    -2.07
     externally
    -2.03
    POSITIVE LOGITS
     Ago
    2.98
     before
    2.91
     ago
    2.87
     hindsight
    2.65
     resumes
    2.64
     BEFORE
    2.55
    before
    2.55
     Later
    2.50
     THEN
    2.49
     hiatus
    2.42
    Activations Density 0.173%

    No Known Activations