© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    references to various literary genres and authors

    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
    0:0.20
    1:0.02
    2:0.12
    3:0.09
    4:0.05
    5:0.12
    6:0.06
    7:0.07
    8:0.11
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
    paio
    -2.83
     deposition
    -2.70
     Hamas
    -2.51
     gol
    -2.50
     Parking
    -2.48
     BCC
    -2.47
    pkg
    -2.38
    tesy
    -2.37
     Drill
    -2.28
     Barclays
    -2.27
    POSITIVE LOGITS
     novels
    4.53
     fiction
    4.34
     Lovecraft
    4.26
     fantasy
    4.22
     sci
    4.11
     Fantasy
    4.04
     fictional
    3.95
     interstellar
    3.85
     dystopian
    3.79
     imaginative
    3.79
    Activations Density 0.089%

    No Known Activations