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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20724
    Prev
    Next
    INDEX
    Explanations

    references to military and strategic keywords

    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
    3:0.05
    4:0.04
    5:0.04
    6:0.28
    7:0.04
    8:0.05
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
     Vaughan
    -4.09
     Gunn
    -3.79
     Morton
    -3.73
     Rapp
    -3.66
    Simon
    -3.58
     Lyft
    -3.58
     Jess
    -3.53
     Simon
    -3.49
    Jess
    -3.47
     Wass
    -3.46
    POSITIVE LOGITS
     BASE
    7.55
     bases
    7.14
     Base
    7.09
     base
    6.89
    base
    6.85
    Base
    6.73
     bunker
    4.98
     bas
    4.68
    abase
    4.49
     barracks
    4.34
    Activations Density 0.008%

    No Known Activations