© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    names of political or military figures

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

    references to specific individuals, events, or actions related to political or social conflicts

    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
    1:0.06
    2:0.13
    3:0.08
    4:0.03
    5:0.02
    6:0.23
    7:0.09
    8:0.04
    9:0.10
    10:0.08
    11:0.08
    Negative Logits
    ngth
    -1.46
    staking
    -1.17
     fluor
    -1.09
    esity
    -1.07
     diets
    -1.06
    icultural
    -1.06
     censored
    -1.05
     advoc
    -1.03
     microsc
    -1.03
     iod
    -1.03
    POSITIVE LOGITS
    gha
    1.20
    aq
    1.20
    hu
    1.15
     Resort
    1.14
    idian
    1.12
     Hamm
    1.08
    adian
    1.08
    aho
    1.08
     Bak
    1.05
     Intermediate
    1.04
    Activations Density 0.028%

    No Known Activations