© 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. 12763
    Prev
    Next
    INDEX
    Explanations

    mentions of people in positions of power and political commentary

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

    phrases related to formal statements or announcements

    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
    0:0.02
    1:0.09
    2:0.12
    3:0.04
    4:0.02
    5:0.08
    6:0.07
    7:0.11
    8:0.12
    9:0.11
    10:0.09
    11:0.07
    Negative Logits
    ',"
    -1.45
    ,'"
    -1.35
    usercontent
    -1.24
    avorite
    -1.05
     branching
    -1.03
     privile
    -1.03
     glim
    -1.02
    illac
    -1.02
    '),
    -1.00
     whichever
    -0.99
    POSITIVE LOGITS
    ecd
    1.24
    Dialogue
    1.10
     briefing
    1.10
     Advice
    1.09
    ibus
    1.06
    reports
    1.01
    �士
    0.98
     briefed
    0.97
    arity
    0.97
     consultations
    0.96
    Activations Density 0.111%

    No Known Activations