© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with rescue operations and humanitarian efforts

    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
    0:0.12
    1:0.03
    2:0.35
    3:0.08
    4:0.04
    5:0.07
    6:0.05
    7:0.04
    8:0.05
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
    IQ
    -3.06
    ium
    -2.49
     IQ
    -2.47
    imentary
    -2.46
     Compton
    -2.46
     Clapper
    -2.44
    donald
    -2.44
    reflect
    -2.38
     NBN
    -2.31
    ibe
    -2.30
    POSITIVE LOGITS
     rescue
    6.77
     rescuing
    6.46
     Rescue
    6.28
     resc
    6.11
     rescued
    5.88
     salvage
    4.51
     drowning
    3.95
     SOS
    3.78
    cue
    3.71
     stranded
    3.69
    Activations Density 0.033%

    No Known Activations