© 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. 5301
    Prev
    Next
    INDEX
    Explanations

    instances of exceeding performance or excellence in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    instances of performing well or excelling in various fields or subjects

    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
    0:0.03
    1:0.02
    2:0.11
    3:0.15
    4:0.03
    5:0.05
    6:0.04
    7:0.06
    8:0.05
    9:0.14
    10:0.07
    11:0.20
    Negative Logits
    soDeliveryDate
    -1.49
    achment
    -1.23
    uphem
    -1.18
     parted
    -1.17
    bands
    -1.16
    leased
    -1.13
    soType
    -1.11
    displayText
    -1.09
     withdrew
    -1.07
     regrets
    -1.07
    POSITIVE LOGITS
    ahime
    1.27
     performance
    1.20
    orer
    1.18
     efficiency
    1.18
     miser
    1.18
     Perform
    1.17
    performing
    1.16
     Excellent
    1.15
    cellent
    1.15
     morale
    1.13
    Activations Density 0.003%

    No Known Activations