© 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. 9521
    Prev
    Next
    INDEX
    Explanations

    statements or claims related to conflict and struggles

    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
    0:0.38
    1:0.02
    2:0.17
    3:0.07
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.04
    9:0.01
    10:0.11
    11:0.03
    Negative Logits
     recommending
    -3.33
     stocking
    -3.17
     recommendations
    -3.07
     recommendation
    -3.00
     downgrade
    -2.91
     shipments
    -2.89
     shipment
    -2.88
    Recomm
    -2.73
     Recomm
    -2.68
     warranties
    -2.62
    POSITIVE LOGITS
     raged
    3.63
     waged
    3.31
     fought
    3.10
     raging
    3.00
    Fight
    2.98
     contest
    2.96
     fierce
    2.93
     battleground
    2.84
    fights
    2.76
     skirm
    2.75
    Activations Density 0.099%

    No Known Activations