© 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. 3-ATT-KK
    11. 6652
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and modal verbs indicating possibility or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.06
    2:0.05
    3:0.02
    4:0.02
    5:0.18
    6:0.09
    7:0.06
    8:0.07
    9:0.12
    10:0.08
    11:0.17
    Negative Logits
     Erica
    -1.38
    411
    -1.33
    united
    -1.31
    waters
    -1.31
     Adin
    -1.30
    irting
    -1.30
     Uriel
    -1.29
     Rober
    -1.27
     Totem
    -1.24
     Tara
    -1.24
    POSITIVE LOGITS
    soever
    2.06
     whatsoever
    1.90
     regardless
    1.86
     except
    1.77
     irrespective
    1.68
     loser
    1.61
    ailable
    1.57
    ichever
    1.57
     unless
    1.56
     anywhere
    1.55
    Activations Density 0.017%

    No Known Activations