© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    references to political figures and media coverage of their actions

    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
    2:0.06
    3:0.17
    4:0.31
    5:0.02
    6:0.02
    7:0.10
    8:0.05
    9:0.05
    10:0.08
    11:0.06
    Negative Logits
     Pis
    -1.52
     Malk
    -1.52
    ipel
    -1.47
     shorthand
    -1.45
     Syl
    -1.43
    oenix
    -1.41
     prest
    -1.38
     Lomb
    -1.37
    ainment
    -1.35
    versible
    -1.34
    POSITIVE LOGITS
     shortcomings
    1.98
     inaction
    1.96
     bullies
    1.82
     advances
    1.75
     perceived
    1.69
     failings
    1.68
     seeming
    1.67
     inconsistencies
    1.63
     intruder
    1.63
     aggress
    1.62
    Activations Density 0.173%

    No Known Activations