© 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. 22500
    Prev
    Next
    INDEX
    Explanations

    words related to historical events, political discussions, and policy activities, with a focus on specific details and narratives

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

    phrases indicating contrast or exceptions in contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.23
    1:0.03
    2:0.06
    3:0.13
    4:0.03
    5:0.10
    6:0.07
    7:0.02
    8:0.06
    9:0.11
    10:0.08
    11:0.02
    Negative Logits
     Blend
    -1.14
     Yep
    -1.12
     dear
    -1.08
     Vampire
    -1.08
     Pick
    -1.04
     Wiz
    -1.03
    Yep
    -1.02
     Mats
    -1.02
    guard
    -1.00
     Picks
    -1.00
    POSITIVE LOGITS
    xual
    1.38
    agara
    1.34
    olson
    1.33
     glim
    1.28
    ihara
    1.25
     acknowled
    1.24
     anecd
    1.24
    glers
    1.17
    lihood
    1.12
    ulton
    1.12
    Activations Density 0.117%

    No Known Activations