© 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. 23000
    Prev
    Next
    INDEX
    Explanations

    names associated with important locations and events

    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
    0:0.42
    1:0.01
    2:0.07
    3:0.12
    4:0.04
    5:0.05
    6:0.02
    7:0.03
    8:0.05
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
     Etsy
    -2.77
     Cthulhu
    -2.63
     scrib
    -2.59
     Hogwarts
    -2.55
     eBay
    -2.51
     handwriting
    -2.46
     Pens
    -2.44
    tumblr
    -2.36
     Dropbox
    -2.34
     Gutenberg
    -2.32
    POSITIVE LOGITS
     broadcaster
    4.07
     camer
    3.75
     airs
    3.74
     broadcast
    3.59
     interviewer
    3.50
     broadcasting
    3.45
     aired
    3.43
     broadcasts
    3.43
     reporter
    3.41
     correspondent
    3.28
    Activations Density 0.187%

    No Known Activations