© 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. 19573
    Prev
    Next
    INDEX
    Explanations

    references to people and organizations

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.07
    4:0.02
    5:0.04
    6:0.08
    7:0.02
    8:0.03
    9:0.56
    10:0.02
    11:0.02
    Negative Logits
     Kling
    -3.87
     Cumber
    -3.28
     Powell
    -3.16
     Ply
    -3.15
    TERN
    -2.96
     Lewis
    -2.90
    rings
    -2.85
     Timber
    -2.82
    lock
    -2.82
     Tibetan
    -2.78
    POSITIVE LOGITS
    AA
    5.45
     Aqua
    5.24
     AA
    4.94
     ASA
    4.90
     Ara
    4.67
     awa
    4.66
    SA
    4.66
    sa
    4.48
    AAA
    4.47
     BA
    4.24
    Activations Density 0.403%

    No Known Activations