© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions, specifically involving traumatic incidents

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    narratives surrounding significant events or controversies

    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
    1:0.11
    2:0.22
    3:0.02
    4:0.03
    5:0.05
    6:0.12
    7:0.16
    8:0.08
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    VERTISEMENT
    -1.66
     contraception
    -1.13
     pilgrims
    -1.13
     STAND
    -1.12
    rogens
    -1.11
     Rider
    -1.09
     ourselves
    -1.06
    rogen
    -1.06
     masc
    -1.05
     Bus
    -1.05
    POSITIVE LOGITS
    iaries
    1.40
    abase
    1.39
    orney
    1.37
    uper
    1.37
    azeera
    1.37
    aughters
    1.35
    zhen
    1.34
    mma
    1.30
    tsy
    1.29
    IFE
    1.27
    Activations Density 0.149%

    No Known Activations