© 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. 11559
    Prev
    Next
    INDEX
    Explanations

    instances of negation and comments about validity or criticism

    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
    0:0.11
    1:0.06
    2:0.06
    3:0.05
    4:0.04
    5:0.03
    6:0.13
    7:0.03
    8:0.03
    9:0.35
    10:0.03
    11:0.02
    Negative Logits
    �
    -3.71
    agara
    -3.56
     beet
    -3.49
     Wak
    -3.48
     Akron
    -3.46
    EB
    -3.35
    Gro
    -3.10
     Beet
    -3.06
     cryst
    -3.06
     Kasich
    -3.04
    POSITIVE LOGITS
     comment
    5.79
    comment
    5.41
     Comments
    5.35
     comments
    5.31
     Comment
    5.28
     commenter
    5.25
     commentary
    5.18
    Comment
    5.10
     commenters
    4.99
     commenting
    4.94
    Activations Density 0.019%

    No Known Activations