© 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. 5-ATT-KK
    11. 44118
    Prev
    Next
    INDEX
    Explanations

    phrases that involve political or social controversy related to elections

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.06
    4:0.07
    5:0.04
    6:0.35
    7:0.06
    8:0.05
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
    phia
    -1.40
    Ro
    -1.38
     Doodle
    -1.36
    GD
    -1.35
     whatsoever
    -1.32
    FB
    -1.31
    Day
    -1.29
    plane
    -1.28
    };
    -1.28
    PRE
    -1.27
    POSITIVE LOGITS
    lished
    1.54
    BuyableInstoreAndOnline
    1.36
     corrid
    1.36
    romising
    1.28
    ikuman
    1.23
     separatist
    1.22
     tiss
    1.21
    zman
    1.19
    urst
    1.18
     prosec
    1.17
    Activations Density 0.002%

    No Known Activations