© 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. 4711
    Prev
    Next
    INDEX
    Explanations

    instances of extreme or polarized language

    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
    0:0.11
    1:0.03
    2:0.10
    3:0.04
    4:0.03
    5:0.04
    6:0.26
    7:0.03
    8:0.04
    9:0.20
    10:0.02
    11:0.03
    Negative Logits
    orio
    -3.58
     SOFTWARE
    -3.58
     intox
    -3.50
    ugu
    -3.45
    wine
    -3.37
     Wass
    -3.35
    AGE
    -3.27
     horn
    -3.26
    angelo
    -3.24
    aughters
    -3.24
    POSITIVE LOGITS
     Flat
    8.50
     flats
    7.37
     flat
    7.14
    flat
    6.45
     flatt
    4.65
     Flo
    4.17
     flattened
    4.07
     squat
    3.95
    Fl
    3.93
     Shard
    3.90
    Activations Density 0.003%

    No Known Activations