© 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. 9-ATT-KK
    11. 17281
    Prev
    Next
    INDEX
    Explanations

    communication regarding threats or harmful intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.01
    2:0.09
    3:0.17
    4:0.03
    5:0.32
    6:0.03
    7:0.06
    8:0.04
    9:0.03
    10:0.06
    11:0.02
    Negative Logits
    entimes
    -2.09
     phones
    -2.02
    atter
    -2.00
     letters
    -1.99
    illions
    -1.93
    essage
    -1.92
    serial
    -1.89
     intercepted
    -1.85
     dots
    -1.84
     eaves
    -1.84
    POSITIVE LOGITS
     WCS
    2.29
     PLAN
    2.16
     SEE
    2.14
    Congratulations
    2.13
    TAG
    2.10
     Congratulations
    2.09
     TEAM
    2.08
    please
    2.08
     congratulations
    2.07
     plans
    2.06
    Activations Density 0.508%

    No Known Activations