© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    elements related to legal actions and claims of fraud or environmental issues

    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
    0:0.19
    1:0.10
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.07
    7:0.13
    8:0.02
    9:0.04
    10:0.13
    11:0.06
    Negative Logits
    oshenko
    -3.09
    Ari
    -3.05
    henko
    -3.00
    ello
    -2.91
     Yuri
    -2.90
    iazep
    -2.86
     polio
    -2.84
    Ali
    -2.76
    Eva
    -2.74
     AVG
    -2.73
    POSITIVE LOGITS
     Timber
    8.63
     timber
    5.87
     lumber
    4.64
     Timbers
    4.50
     logging
    3.43
     Glacier
    3.29
     wood
    3.19
     Portland
    3.12
    Wood
    3.07
     Dock
    2.98
    Activations Density 0.001%

    No Known Activations