© 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. 11140
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to political manipulation and critique

    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
    0:0.06
    1:0.01
    2:0.06
    3:0.43
    4:0.04
    5:0.06
    6:0.02
    7:0.05
    8:0.03
    9:0.02
    10:0.14
    11:0.02
    Negative Logits
     pairs
    -2.73
     pads
    -2.58
     beds
    -2.56
     rooms
    -2.53
    english
    -2.48
     ranges
    -2.42
     servers
    -2.41
     monitors
    -2.39
     streams
    -2.38
     locations
    -2.38
    POSITIVE LOGITS
     betrayal
    3.23
     accomplishment
    3.07
     fallacy
    3.02
     setback
    3.00
     folly
    2.99
     inev
    2.90
     heresy
    2.88
     inconvenience
    2.87
     disgrace
    2.87
     imposition
    2.85
    Activations Density 0.725%

    No Known Activations