© 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. 18487
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence-ending elements that indicate conclusions or transitions in 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
    1:0.04
    2:0.08
    3:0.04
    4:0.07
    5:0.05
    6:0.20
    7:0.06
    8:0.06
    9:0.19
    10:0.04
    11:0.05
    Negative Logits
     Flavoring
    -4.23
     Dupl
    -3.67
     Redmond
    -3.57
    catentry
    -3.54
    adelphia
    -3.53
     Potter
    -3.36
     bilingual
    -3.29
    redo
    -3.24
    opal
    -3.16
    thora
    -3.12
    POSITIVE LOGITS
     Hess
    9.94
     Ness
    4.57
     Huss
    3.90
     Tess
    3.87
    hess
    3.62
     informant
    3.59
     Seymour
    3.56
     Hughes
    3.34
    ESS
    3.34
     Helm
    3.34
    Activations Density 0.000%

    No Known Activations