© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 7121
    Prev
    Next
    INDEX
    Explanations

    instances of retraction or acknowledgment in media contexts

    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
    0:0.41
    1:0.02
    2:0.08
    3:0.07
    4:0.02
    5:0.07
    6:0.05
    7:0.04
    8:0.06
    9:0.05
    10:0.03
    11:0.04
    Negative Logits
    ertodd
    -2.75
    Hamilton
    -2.63
     bridge
    -2.45
     Mn
    -2.42
    Assistant
    -2.34
     裏�
    -2.31
     concrete
    -2.31
     signalling
    -2.29
     Warrant
    -2.27
     EEG
    -2.25
    POSITIVE LOGITS
     magazine
    6.13
    Magazine
    5.78
     magazines
    5.63
    azine
    4.77
     Magazine
    4.73
     editors
    4.35
     Editors
    4.20
     publication
    4.18
    azines
    4.10
    mag
    3.99
    Activations Density 0.103%

    No Known Activations