© 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. 5-ATT-KK
    11. 37177
    Prev
    Next
    INDEX
    Explanations

    references to political challenges and voter engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.10
    3:0.07
    4:0.17
    5:0.02
    6:0.05
    7:0.33
    8:0.04
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    olphin
    -1.67
    geries
    -1.61
    iann
    -1.60
    iked
    -1.59
    ovych
    -1.51
    cember
    -1.42
    chwitz
    -1.42
     petitions
    -1.40
    azar
    -1.37
    anish
    -1.37
    POSITIVE LOGITS
     CoC
    1.47
     Coul
    1.47
     continuity
    1.37
    essential
    1.37
     Outs
    1.36
     Pwr
    1.33
     disruption
    1.32
    Component
    1.32
     workforce
    1.30
    sels
    1.28
    Activations Density 0.002%

    No Known Activations