© 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. 18944
    Prev
    Next
    INDEX
    Explanations

    references to significant events or actions, particularly involving violence or transformation

    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
    0:0.07
    1:0.04
    2:0.07
    3:0.05
    4:0.03
    5:0.05
    6:0.24
    7:0.05
    8:0.05
    9:0.24
    10:0.03
    11:0.04
    Negative Logits
     Citiz
    -3.83
    vv
    -3.77
     coy
    -3.62
     Xavier
    -3.45
     categ
    -3.45
    Cruz
    -3.43
     Wildcats
    -3.37
     Cavs
    -3.31
    otes
    -3.31
    opt
    -3.29
    POSITIVE LOGITS
     Hammer
    10.09
     hammer
    8.78
     hamm
    7.08
    Ham
    6.84
    hammer
    6.82
     HAM
    5.42
     hammered
    5.16
     Flam
    4.83
     Ham
    4.72
     Helm
    4.52
    Activations Density 0.001%

    No Known Activations