© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8264
    Prev
    Next
    INDEX
    Explanations

    statements indicating discussions about legislative processes

    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
    1:0.03
    2:0.11
    3:0.22
    4:0.06
    5:0.14
    6:0.03
    7:0.10
    8:0.04
    9:0.03
    10:0.11
    11:0.02
    Negative Logits
     despised
    -2.40
     falsely
    -2.22
     polluted
    -2.15
     dared
    -2.09
     tricked
    -2.08
     impoverished
    -2.01
     hated
    -1.98
     discriminated
    -1.98
     arrogance
    -1.98
    ustomed
    -1.98
    POSITIVE LOGITS
     timetable
    3.00
     timeframe
    2.86
     TBD
    2.56
     timelines
    2.52
     indications
    2.51
     preliminary
    2.48
     timeline
    2.45
    catentry
    2.33
     TBA
    2.30
     discussions
    2.30
    Activations Density 0.688%

    No Known Activations