© 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. 15103
    Prev
    Next
    INDEX
    Explanations

    references related to laws and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.07
    1:0.03
    2:0.20
    3:0.06
    4:0.21
    5:0.05
    6:0.05
    7:0.03
    8:0.06
    9:0.11
    10:0.04
    11:0.03
    Negative Logits
    Preview
    -1.47
    lined
    -1.38
    ioxide
    -1.38
     Extensions
    -1.34
    =-=-=-=-
    -1.29
    FTWARE
    -1.26
     Preview
    -1.24
    uphem
    -1.24
    ategories
    -1.21
    gradient
    -1.19
    POSITIVE LOGITS
     Butcher
    1.34
     harming
    1.30
     harm
    1.28
     reck
    1.23
     Mortal
    1.19
    ë
    1.17
     spun
    1.16
     eth
    1.14
     Polk
    1.13
     impaired
    1.12
    Activations Density 0.003%

    No Known Activations