© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    names and entities related to corporate or organizational references

    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
    0:0.13
    1:0.22
    2:0.04
    3:0.05
    4:0.02
    5:0.02
    6:0.06
    7:0.14
    8:0.03
    9:0.03
    10:0.17
    11:0.05
    Negative Logits
    Bey
    -2.90
     Wild
    -2.73
     furnace
    -2.69
     Hearth
    -2.63
     bron
    -2.56
     radiant
    -2.48
     blazing
    -2.48
    ◼
    -2.38
     cle
    -2.33
     melan
    -2.31
    POSITIVE LOGITS
    um
    4.84
     Kum
    4.25
     Gum
    3.94
    UM
    3.77
    rum
    3.67
     Um
    3.36
    umar
    3.35
     Cum
    3.28
     Sum
    3.16
    umm
    3.10
    Activations Density 0.007%

    No Known Activations