© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11766
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles within the context of formal communication

    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
    0:0.05
    1:0.04
    2:0.04
    3:0.04
    4:0.06
    5:0.03
    6:0.39
    7:0.03
    8:0.03
    9:0.17
    10:0.03
    11:0.03
    Negative Logits
     McCorm
    -3.93
     McCull
    -3.57
     Gamb
    -3.47
     tamp
    -3.25
    ques
    -3.20
     Wang
    -3.11
    WS
    -3.05
    VL
    -3.05
    kered
    -3.05
    RW
    -3.05
    POSITIVE LOGITS
     Anch
    4.94
     Athe
    4.84
     Aero
    4.64
     atheism
    4.58
     Onion
    4.50
     atheists
    4.43
     Ares
    4.40
     Avenger
    4.36
     ACE
    4.18
     Athena
    4.17
    Activations Density 0.059%

    No Known Activations