© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19815
    Prev
    Next
    INDEX
    Explanations

    references to document metadata or file sizes

    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
    0:0.20
    1:0.02
    2:0.02
    3:0.13
    4:0.24
    5:0.11
    6:0.01
    7:0.06
    8:0.06
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
     satell
    -2.65
     confir
    -2.62
     deduct
    -2.52
     reper
    -2.48
     iod
    -2.42
     ded
    -2.42
     renewed
    -2.36
     OCT
    -2.35
    【
    -2.33
     livest
    -2.30
    POSITIVE LOGITS
     Chambers
    2.71
    bilt
    2.56
    adem
    2.45
    utils
    2.45
    rb
    2.42
    animous
    2.33
    GUI
    2.30
     Graveyard
    2.27
    CSS
    2.27
     Brooks
    2.27
    Activations Density 0.000%

    No Known Activations