© 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. 10-ATT-KK
    11. 7894
    Prev
    Next
    INDEX
    Explanations

    statements and mentions of agreements and contracts related to law enforcement or government oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.09
    3:0.05
    4:0.04
    5:0.03
    6:0.04
    7:0.05
    8:0.42
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
     besides
    -2.52
    ––
    -2.48
     unequ
    -2.37
     before
    -2.37
     as
    -2.35
    û
    -2.33
     ahead
    -2.33
     alongside
    -2.29
     in
    -2.28
    chery
    -2.27
    POSITIVE LOGITS
     To
    7.41
    To
    6.03
     TO
    4.52
     Of
    4.47
     From
    4.15
    to
    3.80
     For
    3.78
     On
    3.75
     By
    3.63
     At
    3.46
    Activations Density 0.018%

    No Known Activations