© 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. 14549
    Prev
    Next
    INDEX
    Explanations

    personal experiences and emotions related to overcoming challenges and seeking support from others

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

    individuals expressing personal experiences and feelings

    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
    0:0.02
    1:0.02
    2:0.15
    3:0.05
    4:0.01
    5:0.02
    6:0.03
    7:0.08
    8:0.25
    9:0.12
    10:0.05
    11:0.13
    Negative Logits
    BuyableInstoreAndOnline
    -1.32
    icides
    -1.19
     Gil
    -1.08
    ocate
    -1.07
    ivable
    -1.06
    ascript
    -1.03
    allery
    -1.01
    aniel
    -0.97
    athon
    -0.95
    ��
    -0.94
    POSITIVE LOGITS
    HEAD
    1.12
    eday
    1.06
    ODY
    1.04
    EMA
    1.04
    INO
    1.03
    henko
    1.03
    INGTON
    1.01
    方
    1.00
    no
    1.00
    ESE
    1.00
    Activations Density 0.051%

    No Known Activations