© 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. 10-ATT-KK
    11. 13946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cast" and its variations in relation to electoral processes or votes

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.03
    4:0.07
    5:0.02
    6:0.03
    7:0.04
    8:0.02
    9:0.12
    10:0.02
    11:0.51
    Negative Logits
     workflow
    -2.36
     infrastructure
    -2.27
     Economy
    -2.23
     methodology
    -2.19
     functionality
    -2.16
     Topic
    -2.12
     Issues
    -2.11
     websites
    -2.08
     website
    -2.03
    topic
    -2.03
    POSITIVE LOGITS
     spell
    2.48
     cast
    2.36
     casts
    2.23
     spells
    2.18
     pall
    2.14
     twilight
    2.08
     buffs
    2.07
     scorn
    2.07
     devils
    2.06
    spell
    2.06
    Activations Density 0.004%

    No Known Activations