© 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. 20404
    Prev
    Next
    INDEX
    Explanations

    mentions of witches and their related practices

    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
    0:0.25
    1:0.07
    2:0.05
    3:0.05
    4:0.06
    5:0.02
    6:0.07
    7:0.11
    8:0.02
    9:0.05
    10:0.14
    11:0.06
    Negative Logits
     Naj
    -3.58
     Mobility
    -3.43
     Qualcomm
    -3.28
    Interstitial
    -3.22
     Xiaomi
    -3.19
    rahim
    -3.12
     Nguyen
    -3.10
    ettel
    -3.01
     Jordanian
    -3.00
     Snapdragon
    -2.98
    POSITIVE LOGITS
     witch
    8.61
     witches
    8.48
     Witches
    7.79
     witchcraft
    7.72
     Witch
    7.36
    witch
    6.34
     sorce
    6.22
     sorcery
    5.27
     Sorce
    4.95
     sorcerer
    4.92
    Activations Density 0.011%

    No Known Activations