© 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. 15989
    Prev
    Next
    INDEX
    Explanations

    references to crime-related events and law enforcement

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.11
    4:0.11
    5:0.47
    6:0.03
    7:0.02
    8:0.01
    9:0.09
    10:0.02
    11:0.03
    Negative Logits
    SPONSORED
    -4.08
    ADVERTISEMENT
    -3.34
     altogether
    -3.28
     resided
    -3.19
     anyways
    -3.16
    )),
    -3.06
     awaited
    -3.06
     moreover
    -2.94
    >)
    -2.94
     nonetheless
    -2.94
    POSITIVE LOGITS
    Has
    2.90
     has
    2.82
     Have
    2.72
     thinks
    2.71
     believes
    2.69
    has
    2.65
    hello
    2.63
    areth
    2.59
     must
    2.56
    auri
    2.52
    Activations Density 0.054%

    No Known Activations