© 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. 3-ATT-KK
    11. 5236
    Prev
    Next
    INDEX
    Explanations

    terminology related to decommissioning processes

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.07
    3:0.20
    4:0.02
    5:0.04
    6:0.08
    7:0.07
    8:0.04
    9:0.06
    10:0.09
    11:0.21
    Negative Logits
    eele
    -1.37
    vana
    -1.25
    ANCE
    -1.19
    hetti
    -1.18
    ARM
    -1.18
     multiplier
    -1.14
    Adv
    -1.13
    Demand
    -1.13
     Preferred
    -1.08
    OA
    -1.08
    POSITIVE LOGITS
    beard
    1.46
     decom
    1.36
     cellul
    1.26
    bats
    1.14
     sediment
    1.10
     mechanic
    1.09
    bourg
    1.09
     graves
    1.08
    utsche
    1.07
    ..........
    1.06
    Activations Density 0.006%

    No Known Activations