© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the nation and its history

    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
    0:0.27
    1:0.01
    2:0.14
    3:0.15
    4:0.02
    5:0.11
    6:0.02
    7:0.06
    8:0.04
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
     referral
    -2.25
     TTC
    -2.22
     descriptions
    -2.11
     MTA
    -2.10
    tracking
    -2.07
     presentations
    -2.04
     notation
    -2.04
     Tracking
    -1.99
     recommendations
    -1.90
     detailing
    -1.88
    POSITIVE LOGITS
     prosper
    2.52
     reformed
    2.37
     overth
    2.18
     greatness
    2.17
     disinteg
    2.11
     tyr
    2.06
     democracy
    1.97
     bombed
    1.96
     electing
    1.95
     patri
    1.95
    Activations Density 0.239%

    No Known Activations