© 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. 596
    Prev
    Next
    INDEX
    Explanations

    references to impeachment processes and political accountability

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.07
    4:0.06
    5:0.04
    6:0.05
    7:0.06
    8:0.06
    9:0.05
    10:0.07
    11:0.38
    Negative Logits
     programme
    -3.90
     programmes
    -3.75
     (£
    -3.58
     favourable
    -3.41
     -
    -3.39
     civilisation
    -3.25
     recognise
    -3.17
     realise
    -3.07
     favourite
    -3.03
     ageing
    -3.02
    POSITIVE LOGITS
    ADVERTISEMENT
    5.27
    .")
    4.05
    .)
    4.00
    ."
    3.94
    ,"
    3.84
     ―
    3.72
    .,"
    3.63
     \"
    3.62
     \'
    3.55
    urai
    3.43
    Activations Density 0.002%

    No Known Activations