© 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. 23788
    Prev
    Next
    INDEX
    Explanations

    proper names and their affiliations in a news context

    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
    0:0.15
    1:0.01
    2:0.02
    3:0.15
    4:0.05
    5:0.03
    6:0.01
    7:0.19
    8:0.04
    9:0.01
    10:0.26
    11:0.03
    Negative Logits
     promptly
    -2.27
    aturday
    -2.19
    recent
    -2.14
     foreseeable
    -2.14
     scrimmage
    -2.05
     blatantly
    -2.02
     WHY
    -2.02
     clearly
    -2.02
    sequently
    -2.00
     bargain
    -1.99
    POSITIVE LOGITS
     Editing
    3.15
    iets
    2.50
    Camera
    2.27
     editing
    2.05
     Editor
    2.03
     subur
    1.93
    idi
    1.89
    hatt
    1.86
     Writing
    1.86
    "}
    1.86
    Activations Density 0.002%

    No Known Activations