© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-ATT-KK
    11. 21217
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to criticism and political debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.01
    2:0.05
    3:0.08
    4:0.09
    5:0.34
    6:0.03
    7:0.04
    8:0.01
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
     realise
    -2.99
     depends
    -2.77
    pires
    -2.73
     realised
    -2.66
    units
    -2.60
     evolves
    -2.57
     determines
    -2.50
    apa
    -2.49
     solves
    -2.49
     consumes
    -2.49
    POSITIVE LOGITS
     praising
    3.91
     suggesting
    3.77
     criticizing
    3.70
     touting
    3.41
    :]
    3.38
     during
    3.31
     saying
    3.29
     slamming
    3.26
     seeming
    3.23
     denouncing
    3.20
    Activations Density 0.721%

    No Known Activations