© 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. 21745
    Prev
    Next
    INDEX
    Explanations

    monetary values and gas tax rates

    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
    0:0.11
    1:0.04
    2:0.03
    3:0.09
    4:0.06
    5:0.07
    6:0.17
    7:0.02
    8:0.03
    9:0.24
    10:0.04
    11:0.04
    Negative Logits
     Haf
    -3.18
     Merry
    -3.14
     Boat
    -3.10
     HA
    -3.08
    Nar
    -2.97
     Healer
    -2.93
     Hier
    -2.92
    MH
    -2.92
     Mess
    -2.91
     Ha
    -2.87
    POSITIVE LOGITS
     cents
    6.19
     cent
    4.31
    cent
    4.20
    ¢
    4.08
     nickel
    3.93
    corn
    3.88
     penn
    3.84
     dollar
    3.68
    acs
    3.66
     Cooke
    3.57
    Activations Density 0.001%

    No Known Activations