© 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. 10-ATT-KK
    11. 8273
    Prev
    Next
    INDEX
    Explanations

    information related to drought conditions and their impact on water supply

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.28
    1:0.05
    2:0.03
    3:0.09
    4:0.07
    5:0.02
    6:0.04
    7:0.16
    8:0.01
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     transsexual
    -4.11
     Ghostbusters
    -3.66
     Valkyrie
    -3.59
     Schne
    -3.33
     Psychiat
    -3.31
     Joker
    -3.22
     Transgender
    -3.14
     Electro
    -3.11
     Surgery
    -3.02
     skating
    -3.00
    POSITIVE LOGITS
     drought
    5.76
     irrigation
    4.71
     irrig
    4.61
     rains
    4.51
     maize
    4.22
     precipitation
    4.10
     rainfall
    4.09
     rain
    3.82
     wildfires
    3.80
     drying
    3.76
    Activations Density 0.022%

    No Known Activations