© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    phrases related to minimalism and efficiency

    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
    0:0.03
    1:0.03
    2:0.10
    3:0.03
    4:0.02
    5:0.04
    6:0.10
    7:0.09
    8:0.04
    9:0.04
    10:0.07
    11:0.36
    Negative Logits
    eday
    -1.28
    ameron
    -1.15
    uesday
    -1.13
    atars
    -1.13
    icion
    -1.10
    essler
    -1.08
    apego
    -1.06
     Berserker
    -1.06
    Tracker
    -1.05
    frey
    -1.05
    POSITIVE LOGITS
     whatsoever
    1.56
     (<
    1.46
     nor
    1.39
     Mandatory
    1.36
     detectable
    1.36
    nor
    1.28
     Required
    1.21
     describ
    1.19
    WARNING
    1.18
     viable
    1.18
    Activations Density 0.009%

    No Known Activations