© 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. 20050
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety measures and precautions

    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
    0:0.08
    1:0.07
    2:0.06
    3:0.05
    4:0.06
    5:0.03
    6:0.05
    7:0.08
    8:0.03
    9:0.04
    10:0.32
    11:0.08
    Negative Logits
     Ferr
    -3.56
     Laf
    -3.43
     Vie
    -3.31
     Cre
    -3.15
     Cantor
    -3.06
    CV
    -3.05
     Gir
    -3.01
     REM
    -3.00
     VG
    -2.99
     Fract
    -2.96
    POSITIVE LOGITS
     st
    7.31
     ste
    3.63
    st
    3.40
     sp
    3.35
     stalk
    3.25
     sts
    3.22
     sting
    3.19
    �
    3.18
     pal
    3.15
     sc
    3.11
    Activations Density 0.017%

    No Known Activations