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

    Neuronpedia

    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. 10587
    Prev
    Next
    INDEX
    Explanations

    busy or active verbs indicating various tasks or actions being undertaken

    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
    0:0.01
    1:0.03
    2:0.07
    3:0.03
    4:0.01
    5:0.04
    6:0.03
    7:0.05
    8:0.16
    9:0.28
    10:0.06
    11:0.18
    Negative Logits
    isable
    -1.14
     equivalents
    -1.09
    Ability
    -1.07
    felt
    -1.06
    fortune
    -1.06
     cf
    -1.06
    tm
    -1.05
    creator
    -1.04
    oire
    -1.04
     proportional
    -1.04
    POSITIVE LOGITS
    �
    1.39
     busy
    1.36
    BIL
    1.19
    ewater
    1.19
    ░
    1.16
     furiously
    1.12
     beaut
    1.09
    ysis
    1.09
    ople
    1.08
    aan
    1.08
    Activations Density 0.003%

    No Known Activations