© 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. 19162
    Prev
    Next
    INDEX
    Explanations

    references to scientific progress and notable figures in scientific history

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.04
    4:0.05
    5:0.03
    6:0.33
    7:0.03
    8:0.05
    9:0.21
    10:0.02
    11:0.03
    Negative Logits
     mattress
    -4.42
     Sach
    -4.32
     Nottingham
    -3.98
     Nightmare
    -3.88
    vironment
    -3.86
     Nichols
    -3.83
     Micha
    -3.69
    Nich
    -3.66
     Willis
    -3.63
     Nicholson
    -3.54
    POSITIVE LOGITS
     Gal
    10.32
    Gal
    10.23
     gal
    8.70
    gal
    7.51
     Gall
    4.92
    Gall
    4.88
     Fer
    4.85
     Galactic
    4.69
     Gallagher
    4.39
     Grav
    4.24
    Activations Density 0.006%

    No Known Activations