© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19315
    Prev
    Next
    INDEX
    Explanations

    sentences that convey wrongdoing or criminal activities

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.06
    4:0.05
    5:0.04
    6:0.03
    7:0.04
    8:0.05
    9:0.03
    10:0.05
    11:0.49
    Negative Logits
     [/
    -3.98
    [/
    -3.20
     ['
    -3.19
     [
    -3.02
     […]
    -2.86
    ],
    -2.82
     '[
    -2.79
     [-
    -2.74
     ["
    -2.56
     fuckin
    -2.53
    POSITIVE LOGITS
    (
    5.13
    ();
    4.37
    ((
    4.11
    ()
    4.09
    Video
    4.08
    ().
    4.03
    ("
    4.02
    (){
    3.78
    (*
    3.77
    poll
    3.76
    Activations Density 0.004%

    No Known Activations