© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12344
    Prev
    Next
    INDEX
    Explanations

    generic terms that are widely applicable across different contexts

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

    phrases indicating comparisons or contrasts involving the term "else."

    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
    0:0.03
    1:0.02
    2:0.12
    3:0.21
    4:0.04
    5:0.03
    6:0.11
    7:0.13
    8:0.05
    9:0.05
    10:0.07
    11:0.09
    Negative Logits
     streng
    -1.46
     sqor
    -1.45
    enegger
    -1.31
    yll
    -1.29
     toget
    -1.29
     predecessors
    -1.24
     mete
    -1.23
     rapes
    -1.23
     kidding
    -1.22
    ivery
    -1.20
    POSITIVE LOGITS
    ensis
    1.36
    opus
    1.33
    aurus
    1.26
     Aman
    1.23
     Kramer
    1.21
     Paradise
    1.18
    nesty
    1.18
     IA
    1.17
     Civ
    1.16
    qt
    1.16
    Activations Density 0.011%

    No Known Activations