© 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. 322
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating conditional statements or hypothetical scenarios

    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
    0:0.07
    1:0.07
    2:0.07
    3:0.09
    4:0.09
    5:0.08
    6:0.10
    7:0.07
    8:0.08
    9:0.09
    10:0.08
    11:0.07
    Negative Logits
     Lucy
    -3.05
     Chloe
    -3.03
     Que
    -3.02
    elight
    -2.84
     Cloak
    -2.73
     Roz
    -2.70
     Blink
    -2.70
     Bailey
    -2.68
     Pick
    -2.68
     Show
    -2.62
    POSITIVE LOGITS
    AMD
    3.27
     Motorola
    3.15
    chnology
    2.96
    Battery
    2.94
     overcl
    2.83
    conom
    2.79
    orsche
    2.78
    mining
    2.72
    edom
    2.69
    gew
    2.69
    Activations Density 0.000%

    No Known Activations