© 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. 5-ATT-KK
    11. 6533
    Prev
    Next
    INDEX
    Explanations

    forms of the phrase "I’ll" or "I will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.01
    1:0.01
    2:0.22
    3:0.07
    4:0.02
    5:0.06
    6:0.13
    7:0.03
    8:0.05
    9:0.03
    10:0.04
    11:0.27
    Negative Logits
     schedules
    -1.78
     Secretary
    -1.73
     Decay
    -1.65
     Schwarzenegger
    -1.60
     Costs
    -1.60
     Dems
    -1.59
     unforeseen
    -1.55
     ALEC
    -1.55
     Funding
    -1.55
     Roose
    -1.54
    POSITIVE LOGITS
    龍
    2.00
    etheless
    1.86
    ibaba
    1.77
    gdala
    1.75
    column
    1.72
    shop
    1.71
    sections
    1.71
     metab
    1.60
    raq
    1.59
    zsche
    1.58
    Activations Density 0.005%

    No Known Activations