© 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. 9010
    Prev
    Next
    INDEX
    Explanations

    references to images and their attribution in the text

    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
    0:0.05
    1:0.03
    2:0.07
    3:0.11
    4:0.11
    5:0.05
    6:0.03
    7:0.09
    8:0.07
    9:0.17
    10:0.09
    11:0.08
    Negative Logits
    entimes
    -2.40
    rawdownloadcloneembedreportprint
    -2.31
     cush
    -2.27
     initiating
    -2.21
     delivering
    -2.20
     tackling
    -2.17
     predetermined
    -2.16
     expecting
    -2.13
     emanc
    -2.12
     paraly
    -2.11
    POSITIVE LOGITS
     Edited
    2.59
     PHOTO
    2.56
     Photography
    2.49
     Airl
    2.48
     Image
    2.36
     Clare
    2.31
    Flickr
    2.29
     Images
    2.28
    Photo
    2.26
     Photographer
    2.24
    Activations Density 0.032%

    No Known Activations