© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 15006
    Prev
    Next
    INDEX
    Explanations

    information related to financial deficits and surpluses in a governmental context

    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
    0:0.07
    1:0.14
    2:0.05
    3:0.06
    4:0.05
    5:0.02
    6:0.12
    7:0.20
    8:0.01
    9:0.04
    10:0.07
    11:0.12
    Negative Logits
     ancestry
    -2.23
    ETA
    -2.19
    エル
    -2.14
    gradation
    -2.04
     Bloody
    -2.02
    river
    -1.92
     GOODMAN
    -1.92
     Conversion
    -1.91
     reciproc
    -1.90
     surname
    -1.85
    POSITIVE LOGITS
     deficit
    4.06
     deficits
    3.11
     surplus
    2.86
    Deb
    2.66
     debt
    2.50
    anke
    2.47
    achus
    2.46
     Debt
    2.36
    luster
    2.16
     sur
    2.16
    Activations Density 0.024%

    No Known Activations