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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8225
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attribution of statements, particularly in quotes

    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
    0:0.07
    1:0.02
    2:0.05
    3:0.12
    4:0.04
    5:0.10
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.35
    11:0.04
    Negative Logits
    rats
    -2.04
    iencies
    -2.01
     transitioned
    -1.94
     ceases
    -1.92
     discontinued
    -1.90
     begins
    -1.86
    bred
    -1.84
    icides
    -1.84
     perfected
    -1.83
     avoided
    -1.82
    POSITIVE LOGITS
     Saying
    3.14
     saying
    3.05
     arguing
    2.51
     insisting
    2.35
     argue
    2.31
     stating
    2.26
     conced
    2.25
     bund
    2.25
     SAY
    2.23
     boasting
    2.23
    Activations Density 0.018%

    No Known Activations