© 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. 9-ATT-KK
    11. 212
    Prev
    Next
    INDEX
    Explanations

    references to political affiliations and members of Congress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.01
    2:0.06
    3:0.34
    4:0.02
    5:0.11
    6:0.04
    7:0.03
    8:0.04
    9:0.01
    10:0.14
    11:0.04
    Negative Logits
     Comput
    -2.31
    estyles
    -2.27
     Designs
    -2.21
    shirts
    -2.13
     Newsp
    -2.12
    ournals
    -2.11
     Zeit
    -2.10
     Machines
    -2.10
     Journals
    -2.09
    IDs
    -2.06
    POSITIVE LOGITS
     thorn
    2.37
     ally
    2.34
     foe
    2.32
     tough
    2.24
     defender
    2.19
     prohib
    2.17
     contentious
    2.17
     prone
    2.16
     embattled
    2.15
     vulnerable
    2.14
    Activations Density 0.055%

    No Known Activations