© 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. 12750
    Prev
    Next
    INDEX
    Explanations

    instances of threats and violence in various contexts

    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
    0:0.03
    1:0.01
    2:0.03
    3:0.04
    4:0.07
    5:0.49
    6:0.03
    7:0.03
    8:0.02
    9:0.14
    10:0.02
    11:0.04
    Negative Logits
    Benef
    -2.85
     Slightly
    -2.68
     realised
    -2.66
    xtap
    -2.62
    '>
    -2.60
     misunder
    -2.57
    sequently
    -2.56
    Increased
    -2.49
    \">
    -2.49
     lately
    -2.48
    POSITIVE LOGITS
     if
    6.09
     unless
    5.87
    unless
    5.00
    if
    4.59
     If
    4.26
     whichever
    4.24
     Unless
    3.99
    If
    3.99
     IF
    3.89
    Unless
    3.78
    Activations Density 0.244%

    No Known Activations