© 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. 21609
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to cost and quality in the context of motels

    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
    0:0.17
    1:0.15
    2:0.05
    3:0.03
    4:0.02
    5:0.03
    6:0.09
    7:0.11
    8:0.02
    9:0.04
    10:0.19
    11:0.06
    Negative Logits
    Í
    -3.10
    sylv
    -2.91
    zb
    -2.79
     Pear
    -2.74
    sonian
    -2.69
    anian
    -2.67
     Slov
    -2.64
     SPL
    -2.64
    zar
    -2.63
    Fine
    -2.62
    POSITIVE LOGITS
     Mot
    8.66
    Mot
    7.26
    mot
    6.08
     mot
    5.80
     MOT
    5.06
     motel
    4.77
     Motor
    4.15
     Mob
    3.86
     Motors
    3.78
     MPG
    3.67
    Activations Density 0.003%

    No Known Activations