© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

    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
    0:0.24
    1:0.02
    2:0.04
    3:0.36
    4:0.01
    5:0.06
    6:0.01
    7:0.02
    8:0.13
    9:0.01
    10:0.03
    11:0.02
    Negative Logits
     singer
    -2.62
     festive
    -2.26
     runes
    -2.23
     clans
    -2.22
     colourful
    -2.21
     tattoos
    -2.21
     punk
    -2.21
     vandal
    -2.19
     partying
    -2.17
     singers
    -2.17
    POSITIVE LOGITS
     Wheeler
    2.48
     Elliott
    2.41
     Curt
    2.38
     Mills
    2.36
    idge
    2.32
     Diss
    2.31
     Howe
    2.29
     Humph
    2.24
     Sachs
    2.21
     Rates
    2.21
    Activations Density 0.040%

    No Known Activations