© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17144
    Prev
    Next
    INDEX
    Explanations

    references to specific museums and their exhibits

    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
    0:0.11
    1:0.02
    2:0.06
    3:0.04
    4:0.04
    5:0.04
    6:0.31
    7:0.03
    8:0.06
    9:0.17
    10:0.02
    11:0.03
    Negative Logits
     Pesh
    -3.64
     Priest
    -3.53
     Delta
    -3.48
    Squ
    -3.48
    obl
    -3.44
     Primal
    -3.38
     Squ
    -3.23
     Bulgar
    -3.17
     Bass
    -3.16
    reen
    -3.12
    POSITIVE LOGITS
     museum
    9.08
     museums
    7.99
     Museum
    7.46
    useum
    6.50
     Smithsonian
    6.13
     Muse
    5.32
     zoo
    4.98
     curator
    4.59
     exhibitions
    4.57
    sonian
    4.46
    Activations Density 0.007%

    No Known Activations