© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 13210
    Prev
    Next
    INDEX
    Explanations

    commands related to database management and configuration settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    commands and actions related to software development and database management

    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
    0:0.34
    1:0.04
    2:0.05
    3:0.03
    4:0.11
    5:0.05
    6:0.08
    7:0.05
    8:0.04
    9:0.02
    10:0.09
    11:0.04
    Negative Logits
    adian
    -1.65
    ansas
    -1.61
    entric
    -1.41
    orea
    -1.37
    obbies
    -1.34
    onomic
    -1.33
    aceous
    -1.33
    itect
    -1.33
    lesiastical
    -1.31
    asus
    -1.29
    POSITIVE LOGITS
     Oo
    1.25
    dir
    1.15
    crop
    1.15
    xon
    1.14
     Winn
    1.12
    xit
    1.12
    esy
    1.10
     compile
    1.03
    LIB
    1.03
     Dug
    1.03
    Activations Density 0.088%

    No Known Activations