© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials science and engineering processes

    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
    0:0.19
    1:0.07
    2:0.06
    3:0.06
    4:0.11
    5:0.02
    6:0.06
    7:0.08
    8:0.03
    9:0.07
    10:0.07
    11:0.12
    Negative Logits
     haun
    -3.25
     Ducks
    -3.11
     Willie
    -3.06
     Franch
    -3.03
     Rampage
    -3.00
     Franchise
    -2.95
     Predators
    -2.87
     Genocide
    -2.86
     Yel
    -2.82
     Salem
    -2.81
    POSITIVE LOGITS
     graphene
    6.51
     nan
    6.11
     semic
    5.50
     polymer
    5.04
     nanop
    4.97
     biom
    4.86
     silicon
    4.80
     nano
    4.68
     photoc
    4.63
     molecular
    4.61
    Activations Density 0.196%

    No Known Activations