© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28198
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians and their actions or statements regarding specific policies or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.18
    3:0.23
    4:0.10
    5:0.03
    6:0.02
    7:0.05
    8:0.05
    9:0.05
    10:0.10
    11:0.12
    Negative Logits
    DragonMagazine
    -1.59
    ermanent
    -1.40
     Dragonbound
    -1.40
    rect
    -1.33
    rored
    -1.30
    folder
    -1.26
    isd
    -1.24
    ratulations
    -1.24
    ezvous
    -1.21
    ickets
    -1.20
    POSITIVE LOGITS
     Corinth
    1.60
     unfairly
    1.59
     ruining
    1.57
     seeming
    1.46
     causing
    1.44
    wcs
    1.43
    cause
    1.42
     misinterpret
    1.42
    nor
    1.40
    etz
    1.37
    Activations Density 0.484%

    No Known Activations