© 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. 10-ATT-KK
    11. 9877
    Prev
    Next
    INDEX
    Explanations

    references to surfing and the ocean ecosystem

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.28
    1:0.04
    2:0.04
    3:0.07
    4:0.06
    5:0.05
    6:0.08
    7:0.07
    8:0.03
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Assy
    -3.99
     AMC
    -3.81
     Centauri
    -3.33
     Stafford
    -3.29
    Bir
    -3.25
    veh
    -3.25
    ─
    -3.13
     Lansing
    -3.11
     Lilith
    -3.06
     Lerner
    -3.05
    POSITIVE LOGITS
     surf
    8.60
     surfing
    8.17
     Surf
    8.16
     Fiji
    4.95
     swell
    4.45
     reef
    4.36
     sur
    4.29
     skate
    4.25
     Richie
    4.24
     beach
    4.24
    Activations Density 0.011%

    No Known Activations