© 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. 15533
    Prev
    Next
    INDEX
    Explanations

    references to media content, particularly videos and music

    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
    0:0.12
    1:0.05
    2:0.04
    3:0.05
    4:0.04
    5:0.05
    6:0.16
    7:0.02
    8:0.02
    9:0.33
    10:0.03
    11:0.04
    Negative Logits
     Carbuncle
    -3.54
     capitals
    -3.52
     Kirin
    -3.33
     Celt
    -3.22
     Fitzpatrick
    -3.04
     Armen
    -3.03
     @@
    -3.02
     Euras
    -2.98
     indexes
    -2.96
    letters
    -2.89
    POSITIVE LOGITS
     videos
    6.93
     YouTube
    6.53
     Videos
    6.51
     Video
    6.24
    Video
    6.22
     video
    6.22
    video
    6.21
     VIDEO
    6.15
    YouTube
    6.02
    videos
    5.84
    Activations Density 0.055%

    No Known Activations