© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19279
    Prev
    Next
    INDEX
    Explanations

    statements and descriptions of styles or categories, particularly in a list or comparative format

    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
    0:0.08
    1:0.04
    2:0.05
    3:0.06
    4:0.03
    5:0.05
    6:0.32
    7:0.04
    8:0.03
    9:0.17
    10:0.04
    11:0.02
    Negative Logits
     Goat
    -4.38
     goat
    -4.08
     ram
    -4.06
     goats
    -3.92
     worms
    -3.83
     worm
    -3.80
     parasite
    -3.77
     mosquito
    -3.61
    Ram
    -3.52
     parasites
    -3.51
    POSITIVE LOGITS
     Style
    7.30
     Styles
    7.13
    Style
    6.93
    Sty
    6.38
    styles
    6.18
     style
    6.05
     styles
    5.80
     styling
    5.61
     Sty
    5.39
    style
    5.32
    Activations Density 0.008%

    No Known Activations