© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations, reports, or ongoing investigations

    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
    0:0.11
    1:0.02
    2:0.07
    3:0.04
    4:0.04
    5:0.07
    6:0.14
    7:0.05
    8:0.13
    9:0.21
    10:0.02
    11:0.05
    Negative Logits
     Yankees
    -3.37
     Hawth
    -3.30
     Yankee
    -3.30
     Calif
    -3.23
    illac
    -3.18
     Izan
    -3.16
     Babe
    -3.11
     Edison
    -3.09
     sperm
    -3.05
     subdivision
    -3.05
    POSITIVE LOGITS
     RT
    10.23
    RT
    8.85
    rt
    5.94
     Kov
    4.05
     Ross
    4.05
    TT
    4.04
     LT
    4.02
     retweet
    4.01
    č
    3.93
     Rost
    3.90
    Activations Density 0.004%

    No Known Activations