© 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. 13302
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and conditions of objects

    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
    0:0.34
    1:0.02
    2:0.13
    3:0.13
    4:0.03
    5:0.06
    6:0.04
    7:0.04
    8:0.04
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
     Restaur
    -2.51
    business
    -2.46
     bookstore
    -2.46
    Edit
    -2.40
     Sanford
    -2.37
     Franç
    -2.33
    advertising
    -2.31
     prose
    -2.30
     Isa
    -2.25
    eries
    -2.25
    POSITIVE LOGITS
     ball
    4.46
     balls
    4.36
     bounces
    3.91
     bouncing
    3.54
     ping
    3.46
     BALL
    3.42
     bounce
    3.29
     puck
    3.25
     ejected
    3.22
     projectiles
    3.22
    Activations Density 0.027%

    No Known Activations