© 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. 12388
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and obligations

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

    commands or actions related to forcing, requiring, or compelling entities to perform certain tasks

    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
    1:0.02
    2:0.06
    3:0.12
    4:0.01
    5:0.03
    6:0.05
    7:0.05
    8:0.16
    9:0.28
    10:0.07
    11:0.07
    Negative Logits
    nces
    -1.28
    milo
    -1.27
    yip
    -1.16
    artisan
    -1.15
    etheless
    -1.12
    lan
    -1.12
    terday
    -1.11
    nown
    -1.11
    apor
    -1.10
    sterdam
    -1.10
    POSITIVE LOGITS
     Quit
    1.26
     reconsider
    1.22
     recal
    1.20
    emonic
    1.11
     rethink
    1.05
     refunds
    1.04
     Territories
    1.02
     cancellation
    1.01
     inquiries
    1.00
     reconnect
    1.00
    Activations Density 0.021%

    No Known Activations