© 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. 17625
    Prev
    Next
    INDEX
    Explanations

    references to news publications and their daily editions

    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
    0:0.16
    1:0.01
    2:0.06
    3:0.14
    4:0.05
    5:0.06
    6:0.10
    7:0.04
    8:0.09
    9:0.01
    10:0.19
    11:0.03
    Negative Logits
     Creed
    -2.60
     Casino
    -2.42
     commenters
    -2.31
     moderators
    -2.13
     commenter
    -2.12
     Aki
    -2.07
     pirates
    -2.06
     Metall
    -2.05
     Reloaded
    -2.04
     waitress
    -2.04
    POSITIVE LOGITS
    DragonMagazine
    3.38
    usalem
    2.78
     Yose
    2.75
    aretz
    2.57
    giene
    2.55
    Cover
    2.54
    erey
    2.41
    PI
    2.33
     Juda
    2.32
    cloth
    2.29
    Activations Density 0.009%

    No Known Activations