© 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. 9-ATT-KK
    11. 12000
    Prev
    Next
    INDEX
    Explanations

    mentions of financial amounts and expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.04
    3:0.02
    4:0.03
    5:0.03
    6:0.24
    7:0.04
    8:0.03
    9:0.34
    10:0.02
    11:0.05
    Negative Logits
     Lub
    -4.06
     Klu
    -3.64
    zees
    -3.38
     Thief
    -3.37
     Loft
    -3.21
     Thames
    -3.18
    rub
    -3.17
    zu
    -3.16
     Reds
    -3.16
     Clippers
    -3.15
    POSITIVE LOGITS
     Ann
    7.51
    ANN
    7.43
     ANN
    7.07
    Ann
    7.00
    ann
    6.47
     ann
    6.23
     Hann
    5.77
     Mann
    5.10
    anni
    4.81
    Anne
    4.59
    Activations Density 0.007%

    No Known Activations