© 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. 9-ATT-KK
    11. 1204
    Prev
    Next
    INDEX
    Explanations

    keywords and commands related to database structures and operations

    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
    0:0.10
    1:0.07
    2:0.11
    3:0.12
    4:0.06
    5:0.07
    6:0.08
    7:0.07
    8:0.06
    9:0.08
    10:0.06
    11:0.07
    Negative Logits
     Vita
    -3.09
     Uncharted
    -2.85
     blockers
    -2.84
     blocker
    -2.78
     Vapor
    -2.71
     tether
    -2.70
     Korra
    -2.70
     Twitch
    -2.69
     projectiles
    -2.59
     filmmakers
    -2.57
    POSITIVE LOGITS
    employ
    4.15
    Employ
    3.74
     Employee
    3.70
     salary
    3.60
     Salary
    3.46
     payroll
    3.43
    PART
    3.34
    rank
    3.27
     rank
    3.25
     employee
    3.22
    Activations Density 0.004%

    No Known Activations