© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10742
    Prev
    Next
    INDEX
    Explanations

    statements and quotes related to political discussions and controversies

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.14
    4:0.04
    5:0.34
    6:0.04
    7:0.07
    8:0.06
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
    ousy
    -2.85
     blinking
    -2.54
     headaches
    -2.41
     grin
    -2.32
     visions
    -2.28
    BuyableInstoreAndOnline
    -2.27
     Shinra
    -2.26
    ipple
    -2.22
     landslide
    -2.18
     plum
    -2.17
    POSITIVE LOGITS
    orously
    2.56
     Participant
    2.50
     Participants
    2.42
    ��
    2.38
    clusively
    2.38
     surrog
    2.37
     Reprodu
    2.32
     contestants
    2.31
    ophon
    2.27
     ongoing
    2.27
    Activations Density 0.156%

    No Known Activations