© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 283
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or situations that are contingent upon conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.07
    3:0.14
    4:0.02
    5:0.06
    6:0.01
    7:0.03
    8:0.02
    9:0.01
    10:0.48
    11:0.02
    Negative Logits
     obedience
    -2.15
     obe
    -2.13
    rite
    -2.02
     respect
    -2.01
    }"
    -1.99
    venants
    -1.97
     obedient
    -1.92
    obbies
    -1.91
     Respect
    -1.86
    Strong
    -1.84
    POSITIVE LOGITS
     anytime
    3.01
     feas
    2.95
     potentially
    2.84
     anywhere
    2.63
     jeopardy
    2.57
    ivably
    2.57
     alternatively
    2.57
     future
    2.51
     someday
    2.48
     anybody
    2.37
    Activations Density 0.418%

    No Known Activations