© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-ATT-KK
    11. 15234
    Prev
    Next
    INDEX
    Explanations

    phrases related to past memories and reflections

    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
    0:0.20
    1:0.07
    2:0.10
    3:0.07
    4:0.03
    5:0.03
    6:0.10
    7:0.13
    8:0.02
    9:0.05
    10:0.11
    11:0.04
    Negative Logits
     cigars
    -3.01
     Wu
    -2.90
     UCS
    -2.82
     pyramid
    -2.75
     Hearthstone
    -2.75
    ghai
    -2.62
    wrapper
    -2.56
     IPv
    -2.54
     Puerto
    -2.53
    ramid
    -2.53
    POSITIVE LOGITS
     Clarke
    8.70
    Clar
    6.77
     Jasper
    4.08
     Calder
    3.97
     Lex
    3.52
     Lynn
    3.28
     Bowman
    3.22
     Kelley
    3.21
     Byrne
    3.16
     Yates
    3.09
    Activations Density 0.007%

    No Known Activations