© 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. 12627
    Prev
    Next
    INDEX
    Explanations

    instances of boards and their configurations or descriptions in various contexts

    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
    0:0.13
    1:0.03
    2:0.04
    3:0.04
    4:0.04
    5:0.04
    6:0.29
    7:0.02
    8:0.04
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
     Lambert
    -3.82
     tamp
    -3.71
     Juliet
    -3.62
    Dom
    -3.58
     Hussein
    -3.57
     menstru
    -3.46
     Mas
    -3.46
    Mas
    -3.41
     scent
    -3.39
     Ming
    -3.39
    POSITIVE LOGITS
    Board
    8.26
     boards
    7.99
     Boards
    7.80
     board
    7.67
     Board
    7.31
    board
    7.17
    boards
    6.77
    boarding
    5.95
     boarding
    5.71
    oard
    4.80
    Activations Density 0.019%

    No Known Activations