© 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. 296
    Prev
    Next
    INDEX
    Explanations

    references to significant items or phenomena in a context suggesting analysis or evaluation

    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
    0:0.39
    1:0.03
    2:0.10
    3:0.07
    4:0.04
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.05
    10:0.09
    11:0.03
    Negative Logits
     pods
    -2.50
    Brave
    -2.23
    romeda
    -2.19
     upd
    -2.14
    Gy
    -2.14
    rons
    -2.13
    byss
    -2.10
     experiment
    -2.07
    mates
    -2.05
     Cran
    -2.04
    POSITIVE LOGITS
     references
    3.95
    reference
    3.61
     reference
    3.49
     referencing
    3.45
     mentions
    3.34
     Reference
    3.19
    Reference
    3.05
     References
    3.04
     mentioning
    2.99
     referenced
    2.95
    Activations Density 0.002%

    No Known Activations