© 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. 5436
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparison or description

    oai_token-act-pair · gpt-4o-mini
    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
    0:0.01
    1:0.03
    2:0.07
    3:0.06
    4:0.01
    5:0.05
    6:0.04
    7:0.04
    8:0.11
    9:0.38
    10:0.08
    11:0.06
    Negative Logits
     partName
    -1.27
     assemble
    -1.20
    urden
    -1.15
     persuade
    -1.14
     conclud
    -1.12
     alone
    -1.11
     deceive
    -1.11
     mustache
    -1.10
     Curiosity
    -1.10
     recl
    -1.09
    POSITIVE LOGITS
     Allaah
    1.31
    shi
    1.25
    Fax
    1.24
    unal
    1.23
    ogh
    1.23
    gars
    1.23
    MSN
    1.20
    SourceFile
    1.20
     TAMADRA
    1.20
    verty
    1.16
    Activations Density 0.023%

    No Known Activations