© 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. 21660
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to functions

    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
    1:0.05
    2:0.07
    3:0.13
    4:0.04
    5:0.13
    6:0.16
    7:0.07
    8:0.04
    9:0.04
    10:0.04
    11:0.09
    Negative Logits
     trainers
    -2.55
     Rik
    -2.54
    ``
    -2.47
     diplomacy
    -2.37
     Rag
    -2.27
     Mari
    -2.23
     tag
    -2.17
     Dag
    -2.17
     trainer
    -2.16
     brut
    -2.15
    POSITIVE LOGITS
    venue
    3.02
    mu
    2.88
    Pie
    2.83
    volume
    2.77
    partial
    2.63
     Yellowstone
    2.62
    minecraft
    2.60
    spl
    2.58
    Interstitial
    2.56
    athe
    2.55
    Activations Density 0.003%

    No Known Activations