© 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. 44486
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and 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
    0:0.01
    1:0.00
    2:0.24
    3:0.17
    4:0.09
    5:0.03
    6:0.04
    7:0.08
    8:0.05
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
     Chiefs
    -1.58
     Forth
    -1.55
     Instrument
    -1.53
     Arms
    -1.45
     Ballistic
    -1.40
     Amb
    -1.38
     Vital
    -1.37
     Explos
    -1.36
     Mutual
    -1.33
     Boom
    -1.31
    POSITIVE LOGITS
    qqa
    1.66
    ebin
    1.59
    ール
    1.42
    ead
    1.40
    models
    1.40
    culus
    1.35
    mouse
    1.33
     pens
    1.32
     indefinitely
    1.32
     swamp
    1.30
    Activations Density 0.003%

    No Known Activations