© 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. 11141
    Prev
    Next
    INDEX
    Explanations

    sentences that express harm or potential danger

    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
    0:0.07
    1:0.03
    2:0.07
    3:0.03
    4:0.06
    5:0.04
    6:0.16
    7:0.05
    8:0.09
    9:0.28
    10:0.03
    11:0.04
    Negative Logits
     Antar
    -3.82
     Laos
    -3.73
     Ser
    -3.61
    Magikarp
    -3.58
     Planes
    -3.55
     Mickey
    -3.54
    Nar
    -3.48
     nar
    -3.43
     Marine
    -3.43
     Stones
    -3.42
    POSITIVE LOGITS
     Rebecca
    8.65
    becca
    6.04
     Reb
    4.60
    beck
    3.68
    abe
    3.66
    Reb
    3.66
    bern
    3.53
    resp
    3.52
    eva
    3.45
    Rev
    3.37
    Activations Density 0.001%

    No Known Activations