© 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. 11057
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions that indicate a contrast or exception

    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
    1:0.05
    2:0.08
    3:0.08
    4:0.05
    5:0.07
    6:0.05
    7:0.31
    8:0.06
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
     payday
    -2.80
    Companies
    -2.80
     Flavoring
    -2.79
     wealthier
    -2.75
     casinos
    -2.75
     casino
    -2.68
     wealthy
    -2.68
     pharmaceutical
    -2.59
    illac
    -2.59
     riches
    -2.58
    POSITIVE LOGITS
    LET
    2.68
    CHA
    2.67
    PsyNetMessage
    2.50
    ゴ
    2.47
    Dialogue
    2.46
    letter
    2.44
     裏�
    2.42
    HAM
    2.42
    isin
    2.38
    determination
    2.35
    Activations Density 0.001%

    No Known Activations