© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5782
    Prev
    Next
    INDEX
    Explanations

    mentions of specific series and events in media and their corresponding details

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.01
    2:0.03
    3:0.30
    4:0.03
    5:0.06
    6:0.01
    7:0.06
    8:0.03
    9:0.01
    10:0.30
    11:0.04
    Negative Logits
     pronounce
    -2.25
     hesitated
    -2.24
     arguments
    -2.23
     bruised
    -2.17
     blows
    -2.13
     verbal
    -2.09
     exagger
    -2.07
     unanim
    -2.05
     tended
    -2.05
     complains
    -2.05
    POSITIVE LOGITS
    +.
    2.67
    ™:
    2.66
    !!!
    2.40
    ®
    2.37
    !".
    2.36
    !.
    2.34
     Warehouse
    2.33
     Collabor
    2.32
    )!
    2.31
    Series
    2.31
    Activations Density 0.778%

    No Known Activations