© 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. 20147
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their accompanying conjunctions or qualifiers

    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
    0:0.07
    1:0.04
    2:0.09
    3:0.05
    4:0.05
    5:0.05
    6:0.19
    7:0.04
    8:0.06
    9:0.22
    10:0.05
    11:0.03
    Negative Logits
     Baton
    -3.87
    BAT
    -3.70
    array
    -3.61
     Radeon
    -3.56
     Jaguar
    -3.42
    bat
    -3.42
     sterling
    -3.41
    ira
    -3.39
     Formula
    -3.37
    ���
    -3.33
    POSITIVE LOGITS
     creep
    8.44
     Creep
    8.41
     creeps
    7.43
     creepy
    5.70
     creeping
    5.38
    cre
    5.04
     crept
    4.92
     crawl
    4.36
    Cre
    4.32
     crawled
    4.23
    Activations Density 0.000%

    No Known Activations