© 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. 5-ATT-KK
    11. 41195
    Prev
    Next
    INDEX
    Explanations

    incidents of violence or crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.03
    3:0.10
    4:0.03
    5:0.14
    6:0.01
    7:0.02
    8:0.09
    9:0.20
    10:0.19
    11:0.09
    Negative Logits
    ":"/
    -1.31
    canon
    -1.31
    ocracy
    -1.19
    odox
    -1.18
     incumb
    -1.16
    ibliography
    -1.16
    Conclusion
    -1.16
    peak
    -1.13
    enhagen
    -1.10
    ivably
    -1.10
    POSITIVE LOGITS
     gunfire
    1.27
    ADVERTISEMENT
    1.26
     CCTV
    1.22
     gunman
    1.21
     attacker
    1.18
     assailant
    1.08
     intruder
    1.07
     Saturday
    1.07
    SPONSORED
    1.07
     stabbing
    1.06
    Activations Density 0.353%

    No Known Activations