© 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. 15738
    Prev
    Next
    INDEX
    Explanations

    discussions about movie performance and box office results

    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
    0:0.40
    1:0.02
    2:0.04
    3:0.09
    4:0.03
    5:0.12
    6:0.02
    7:0.05
    8:0.05
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
     Recipes
    -2.40
     authored
    -2.32
     Crafting
    -2.25
     recipes
    -2.21
    Posts
    -2.19
     journal
    -2.15
     typew
    -2.08
     publishes
    -2.06
     Tablet
    -2.04
     handwriting
    -2.00
    POSITIVE LOGITS
     theaters
    3.48
     screenings
    2.85
     theater
    2.48
     theat
    2.48
    osure
    2.39
     Cinema
    2.30
     theatrical
    2.23
    inem
    2.23
     exhib
    2.22
     cinema
    2.20
    Activations Density 0.117%

    No Known Activations