© 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. 18342
    Prev
    Next
    INDEX
    Explanations

    references to panels and presentations

    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
    0:0.12
    1:0.04
    2:0.04
    3:0.04
    4:0.06
    5:0.04
    6:0.23
    7:0.02
    8:0.05
    9:0.24
    10:0.02
    11:0.05
    Negative Logits
     toile
    -3.93
     Teddy
    -3.55
     Bie
    -3.39
     Teach
    -3.29
     Beaver
    -3.29
     smelling
    -3.23
     compost
    -3.10
     Molly
    -3.10
     saints
    -3.08
     hasht
    -3.04
    POSITIVE LOGITS
     Panel
    9.63
    Panel
    8.93
     panel
    8.72
    panel
    8.48
     panels
    8.05
    pan
    4.69
     PAN
    4.62
    Pan
    4.55
     Pan
    4.52
     Chan
    3.89
    Activations Density 0.007%

    No Known Activations