© 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. 13747
    Prev
    Next
    INDEX
    Explanations

    words related to political contests and delegate counts

    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
    0:0.02
    1:0.03
    2:0.04
    3:0.09
    4:0.10
    5:0.23
    6:0.08
    7:0.06
    8:0.02
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     VIDEOS
    -2.89
     realised
    -2.65
    ogical
    -2.52
    obyl
    -2.41
     Changed
    -2.40
    assies
    -2.38
    assadors
    -2.34
    mitter
    -2.29
     apologised
    -2.27
     ALWAYS
    -2.26
    POSITIVE LOGITS
    vote
    3.26
     turnout
    3.23
     polling
    3.19
     winning
    3.05
     landslide
    3.04
     caucuses
    3.04
     independents
    3.02
     among
    2.97
     endorsements
    2.96
     garner
    2.94
    Activations Density 0.285%

    No Known Activations