© 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. 18418
    Prev
    Next
    INDEX
    Explanations

    references to "lines" that denote significant boundary markers or thresholds in various contexts

    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
    0:0.13
    1:0.03
    2:0.09
    3:0.17
    4:0.03
    5:0.05
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.29
    11:0.02
    Negative Logits
     revolves
    -2.31
     upkeep
    -2.22
     nutshell
    -2.10
     Cul
    -2.09
    ogy
    -2.04
     Meow
    -2.01
     Bauer
    -2.00
    rix
    -1.97
     suites
    -1.97
     studios
    -1.96
    POSITIVE LOGITS
     threshold
    3.16
     crossings
    3.10
     brink
    2.95
    cross
    2.86
     crosses
    2.86
     crossed
    2.74
     crossing
    2.74
    auntlet
    2.54
     thresholds
    2.53
     ceasefire
    2.51
    Activations Density 0.016%

    No Known Activations