© 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. 2-ATT-KK
    11. 15305
    Prev
    Next
    INDEX
    Explanations

    phrases related to economics, politics, and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.11
    3:0.07
    4:0.04
    5:0.18
    6:0.06
    7:0.06
    8:0.06
    9:0.07
    10:0.14
    11:0.06
    Negative Logits
    Newsletter
    -0.98
     Powered
    -0.98
     Millennium
    -0.98
     thug
    -0.94
     Premium
    -0.93
     shortly
    -0.92
     Fel
    -0.89
     round
    -0.89
    top
    -0.89
     Fury
    -0.89
    POSITIVE LOGITS
    bda
    1.33
    etheless
    1.21
     Byz
    1.09
     Bulg
    1.06
     Judaism
    1.05
     ancest
    1.05
    xual
    1.05
     Flavoring
    1.04
    idth
    1.02
    ONSORED
    1.01
    Activations Density 0.645%

    No Known Activations