© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 13733
    Prev
    Next
    INDEX
    Explanations

    references to key individuals or leaders in various contexts

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.26
    4:0.02
    5:0.04
    6:0.02
    7:0.04
    8:0.03
    9:0.01
    10:0.35
    11:0.05
    Negative Logits
     continuum
    -2.67
     continuity
    -2.34
     considerably
    -2.26
     proble
    -2.05
     tradition
    -2.04
     phenomen
    -2.03
     conflic
    -2.02
     workflow
    -1.98
     indefinitely
    -1.93
     warr
    -1.93
    POSITIVE LOGITS
     debuted
    2.49
     mocked
    2.38
     unveiled
    2.34
     inquired
    2.33
     aired
    2.32
     questioned
    2.31
    outed
    2.30
     premiered
    2.27
    opened
    2.23
     announced
    2.23
    Activations Density 0.092%

    No Known Activations