© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 6600
    Prev
    Next
    INDEX
    Explanations

    instances of referencing or receiving messages in code contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.12
    2:0.05
    3:0.14
    4:0.02
    5:0.01
    6:0.13
    7:0.06
    8:0.02
    9:0.03
    10:0.26
    11:0.04
    Negative Logits
    Tam
    -4.87
     Tam
    -3.71
     tam
    -3.67
     Hag
    -3.00
     Hague
    -2.96
     Teg
    -2.96
    ahime
    -2.95
    Madison
    -2.93
     Tir
    -2.89
    sels
    -2.89
    POSITIVE LOGITS
     Rec
    8.80
     rec
    7.46
    rec
    7.05
    Rec
    6.96
     REC
    6.62
    REC
    5.00
     recite
    4.37
     recursive
    4.30
     Recon
    4.06
     recru
    3.94
    Activations Density 0.010%

    No Known Activations