© 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. 11024
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their sequences in the text

    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
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.26
    7:0.05
    8:0.09
    9:0.18
    10:0.03
    11:0.03
    Negative Logits
     Bash
    -3.76
     Crosby
    -3.74
     Str
    -3.57
     Stranger
    -3.52
     Ely
    -3.43
    Rog
    -3.30
     Wells
    -3.29
     Lazarus
    -3.29
     Sinclair
    -3.27
     hash
    -3.26
    POSITIVE LOGITS
     Mau
    10.61
     Piet
    8.05
     Kau
    5.44
     Hawai
    4.80
     Hawaii
    4.75
     Honolulu
    4.68
     Hawaiian
    4.53
     NAV
    4.41
    olulu
    4.12
     Lau
    4.08
    Activations Density 0.001%

    No Known Activations