© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    instances of specific medical situations or procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to medical treatment and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.08
    3:0.07
    4:0.02
    5:0.03
    6:0.04
    7:0.18
    8:0.23
    9:0.08
    10:0.05
    11:0.12
    Negative Logits
    soDeliveryDate
    -1.52
    BALL
    -1.07
    mma
    -1.00
    utenberg
    -0.99
     Tiff
    -0.96
     largeDownload
    -0.95
     Mour
    -0.94
     widgets
    -0.94
     astronomer
    -0.93
    Dialog
    -0.92
    POSITIVE LOGITS
     anymore
    1.34
    any
    1.33
     slightest
    1.32
     nor
    1.19
     any
    1.14
    license
    1.08
    anything
    1.05
    minist
    1.05
     dime
    1.05
    acia
    1.04
    Activations Density 0.007%

    No Known Activations