© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 23036
    Prev
    Next
    INDEX
    Explanations

    financial figures or monetary amounts related to projects, budgets, and investments

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.07
    2:0.08
    3:0.13
    4:0.03
    5:0.02
    6:0.04
    7:0.15
    8:0.08
    9:0.05
    10:0.20
    11:0.04
    Negative Logits
     Teg
    -2.51
     Zub
    -2.42
     Tuc
    -2.37
     Bulgar
    -2.25
     Estonia
    -2.21
     fres
    -2.14
     Slov
    -2.13
    Tes
    -2.12
     hasht
    -2.12
    Hash
    -2.08
    POSITIVE LOGITS
     mil
    2.51
     CLSID
    2.31
    ona
    2.28
     million
    2.27
     m
    2.22
     Related
    2.21
    %%%%
    2.16
     Mortgage
    2.08
     Draper
    2.04
    arrell
    2.02
    Activations Density 0.026%

    No Known Activations