© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    terms related to presidential elections and political affiliations

    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
    0:0.06
    1:0.05
    2:0.02
    3:0.08
    4:0.04
    5:0.03
    6:0.22
    7:0.29
    8:0.02
    9:0.06
    10:0.02
    11:0.07
    Negative Logits
    roman
    -2.68
     Pilot
    -2.67
     Squadron
    -2.43
     Customer
    -2.35
     Investig
    -2.31
     Passenger
    -2.30
     QC
    -2.24
     Customers
    -2.22
     Appeal
    -2.20
     insurers
    -2.19
    POSITIVE LOGITS
    cand
    3.02
     candidacy
    2.81
     nominating
    2.79
     candidate
    2.60
    opot
    2.58
     recount
    2.56
     Biden
    2.50
     candidates
    2.49
     bir
    2.48
     nominate
    2.45
    Activations Density 0.035%

    No Known Activations