© 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. 675
    Prev
    Next
    INDEX
    Explanations

    references to significant changes or modifications in processes or systems

    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
    0:0.10
    1:0.02
    2:0.06
    3:0.04
    4:0.13
    5:0.04
    6:0.18
    7:0.06
    8:0.07
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
    wine
    -3.02
     Drain
    -2.80
    Beer
    -2.60
    Buff
    -2.50
     Dough
    -2.46
    Ball
    -2.43
     tavern
    -2.42
    Bur
    -2.41
     duck
    -2.35
    agate
    -2.34
    POSITIVE LOGITS
     MAC
    4.03
     IPS
    3.60
     ASD
    3.42
     NEC
    3.40
     SAM
    3.39
     CST
    3.29
     MO
    3.29
     CMS
    3.26
     CET
    3.23
     CLS
    3.23
    Activations Density 0.053%

    No Known Activations