© 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. 20337
    Prev
    Next
    INDEX
    Explanations

    financial allocations and expenditures related to funding and support initiatives

    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
    0:0.03
    1:0.04
    2:0.04
    3:0.06
    4:0.10
    5:0.11
    6:0.07
    7:0.13
    8:0.02
    9:0.25
    10:0.03
    11:0.06
    Negative Logits
    ITNESS
    -2.41
    ulz
    -2.38
    ウス
    -2.21
     Vers
    -2.06
    picture
    -2.00
    azeera
    -1.98
    yet
    -1.96
     Solution
    -1.93
    lihood
    -1.91
     agre
    -1.90
    POSITIVE LOGITS
     recipients
    2.42
     reimb
    2.41
     diverted
    2.37
     reimburse
    2.30
     reinvest
    2.28
     recipient
    2.25
     donated
    2.24
    nell
    2.15
     funnel
    2.11
     ear
    2.04
    Activations Density 0.075%

    No Known Activations