© 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 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. 22324
    Prev
    Next
    INDEX
    Explanations

    plural forms of nouns or the presence of the letter "s"

    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
    0:0.04
    1:0.02
    2:0.02
    3:0.17
    4:0.02
    5:0.03
    6:0.11
    7:0.03
    8:0.03
    9:0.03
    10:0.38
    11:0.07
    Negative Logits
     veto
    -2.33
    "]
    -2.16
     positively
    -2.04
     expertise
    -1.97
     earnest
    -1.89
     upfront
    -1.85
     dearly
    -1.83
     quo
    -1.83
     bragging
    -1.78
     proverb
    -1.77
    POSITIVE LOGITS
    )/
    3.82
    )'
    3.14
    )=
    2.98
    )+
    2.90
    ){
    2.86
    )\
    2.81
    )=(
    2.68
    )</
    2.68
    )}
    2.67
    )(
    2.60
    Activations Density 0.011%

    No Known Activations