© 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. 10-ATT-KK
    11. 19806
    Prev
    Next
    INDEX
    Explanations

    references to copyright infringement and related legal issues on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.04
    2:0.17
    3:0.08
    4:0.04
    5:0.01
    6:0.09
    7:0.11
    8:0.02
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     Celt
    -3.04
     Azerb
    -3.02
     Fitzgerald
    -2.97
    Sov
    -2.94
     bom
    -2.91
     Sinn
    -2.91
     Fitz
    -2.91
     Guatem
    -2.85
    lein
    -2.80
     Lans
    -2.80
    POSITIVE LOGITS
     YouTube
    8.04
    YouTube
    7.74
     Youtube
    6.34
     youtube
    6.08
    youtube
    5.56
     videos
    5.37
    outube
    5.27
     Videos
    5.12
     Video
    4.48
     Twitch
    4.42
    Activations Density 0.049%

    No Known Activations