© 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. 10-ATT-KK
    11. 9041
    Prev
    Next
    INDEX
    Explanations

    references to royalty payments and related financial aspects in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.06
    2:0.06
    3:0.06
    4:0.06
    5:0.02
    6:0.18
    7:0.14
    8:0.01
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
     Goff
    -3.12
    ワン
    -2.82
    ussen
    -2.66
    opal
    -2.55
     ram
    -2.44
    ugen
    -2.44
    acci
    -2.40
    sych
    -2.40
    itudinal
    -2.38
     diagonal
    -2.36
    POSITIVE LOGITS
     royalty
    6.97
     royalties
    6.75
     patents
    3.73
     patent
    3.40
     licensing
    3.32
     revenues
    3.17
     revenue
    3.12
     taxes
    3.02
     payments
    3.02
    yrights
    2.96
    Activations Density 0.002%

    No Known Activations