© 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. 20245
    Prev
    Next
    INDEX
    Explanations

    terms related to looming threats or dangers

    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
    0:0.44
    1:0.02
    2:0.08
    3:0.07
    4:0.03
    5:0.04
    6:0.02
    7:0.03
    8:0.05
    9:0.02
    10:0.12
    11:0.02
    Negative Logits
    ymes
    -2.70
     homebrew
    -2.62
     pedal
    -2.53
     carts
    -2.47
     recipes
    -2.43
     plagiar
    -2.40
     PCR
    -2.39
    �
    -2.39
     Recipes
    -2.37
     sequencing
    -2.32
    POSITIVE LOGITS
     looms
    3.07
     pall
    3.04
     glare
    3.01
    bright
    2.79
    picture
    2.79
    shadow
    2.79
     glared
    2.78
     draped
    2.78
     hangs
    2.77
     looming
    2.77
    Activations Density 0.007%

    No Known Activations