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

    Neuronpedia

    Jacobian LensNEW
    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. 5-ATT-KK
    11. 28090
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs regarding capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.05
    3:0.06
    4:0.26
    5:0.04
    6:0.20
    7:0.08
    8:0.06
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
     constitu
    -1.66
    undrum
    -1.50
     setback
    -1.50
     Trin
    -1.35
     ordeal
    -1.35
    ゴン
    -1.35
     predicament
    -1.33
     trajectory
    -1.33
     Triple
    -1.32
     significance
    -1.31
    POSITIVE LOGITS
     sake
    1.68
     lest
    1.52
    undo
    1.43
    don
    1.42
    ranged
    1.37
    iates
    1.36
    ptives
    1.31
     instead
    1.29
    docs
    1.26
    urat
    1.26
    Activations Density 0.028%

    No Known Activations