© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    phrases associated with instructions or warnings against making mistakes

    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
    0:0.06
    1:0.06
    2:0.04
    3:0.18
    4:0.06
    5:0.05
    6:0.03
    7:0.03
    8:0.04
    9:0.05
    10:0.28
    11:0.07
    Negative Logits
    icable
    -2.48
    ability
    -2.42
    atively
    -2.33
    CONCLUS
    -2.15
     comparatively
    -2.11
     independently
    -2.11
    ENDED
    -2.08
    confirmed
    -2.07
    ABLE
    -2.06
     marginally
    -2.02
    POSITIVE LOGITS
     vow
    2.32
     hurry
    2.30
     tatt
    2.22
    wagen
    2.21
     liar
    2.14
     Lover
    2.12
     bets
    2.12
    �
    2.09
    repeat
    2.08
    )</
    2.07
    Activations Density 0.014%

    No Known Activations