© 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. 36198
    Prev
    Next
    INDEX
    Explanations

    references to prominent political figures and their statements

    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
    0:0.03
    1:0.03
    2:0.02
    3:0.03
    4:0.02
    5:0.30
    6:0.02
    7:0.01
    8:0.06
    9:0.13
    10:0.17
    11:0.12
    Negative Logits
    cgi
    -1.33
    region
    -1.30
    Torrent
    -1.16
    auna
    -1.13
    notation
    -1.10
     Torrent
    -1.10
     GPL
    -1.10
    /-
    -1.08
    ibrary
    -1.07
    abases
    -1.07
    POSITIVE LOGITS
     praises
    1.24
    ′
    1.21
     inaug
    1.19
    theless
    1.19
     intim
    1.17
     himself
    1.17
    DonaldTrump
    1.16
     shrew
    1.14
     personally
    1.14
     advisers
    1.13
    Activations Density 0.590%

    No Known Activations