© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22418
    Prev
    Next
    INDEX
    Explanations

    quotes and references to dialogue in the text

    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
    0:0.07
    1:0.04
    2:0.06
    3:0.04
    4:0.06
    5:0.05
    6:0.24
    7:0.05
    8:0.07
    9:0.17
    10:0.04
    11:0.06
    Negative Logits
     tribes
    -3.87
     Samurai
    -3.60
     hous
    -3.57
    incinn
    -3.53
     rooting
    -3.52
     stitches
    -3.39
     Pag
    -3.36
     tribe
    -3.32
     Bengals
    -3.32
     stitching
    -3.30
    POSITIVE LOGITS
     Maxwell
    10.47
     Kepler
    6.67
    Max
    5.06
    maxwell
    5.04
     Elon
    4.79
     Kelvin
    4.69
     Mercer
    4.41
     Lionel
    4.15
     Faust
    4.15
     Lever
    4.13
    Activations Density 0.001%

    No Known Activations