© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43233
    Prev
    Next
    INDEX
    Explanations

    mentions of political candidacy and election-related terms

    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
    0:0.03
    1:0.01
    2:0.07
    3:0.07
    4:0.09
    5:0.06
    6:0.03
    7:0.05
    8:0.07
    9:0.05
    10:0.34
    11:0.08
    Negative Logits
    cture
    -1.78
    ashington
    -1.69
    reated
    -1.67
    urdue
    -1.57
     Libraries
    -1.56
    ilities
    -1.55
    obar
    -1.55
     degrade
    -1.55
    ichick
    -1.53
    artisan
    -1.46
    POSITIVE LOGITS
    soDeliveryDate
    2.16
    Cand
    2.15
     frontrunner
    2.12
     candidacy
    1.96
     candidates
    1.93
     candidate
    1.92
     contender
    1.83
    isSpecialOrderable
    1.82
     prospects
    1.80
    Party
    1.75
    Activations Density 0.004%

    No Known Activations