© 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. 19125
    Prev
    Next
    INDEX
    Explanations

    instances of public response and sentiment, particularly criticism and support, related to political events

    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
    0:0.07
    1:0.01
    2:0.05
    3:0.13
    4:0.03
    5:0.07
    6:0.02
    7:0.09
    8:0.03
    9:0.01
    10:0.43
    11:0.02
    Negative Logits
     vantage
    -2.16
     objective
    -2.06
     maxim
    -1.88
    mere
    -1.87
    ighters
    -1.82
     pretend
    -1.81
    pheus
    -1.79
     relax
    -1.78
    tera
    -1.76
     lies
    -1.76
    POSITIVE LOGITS
     backlash
    2.29
    due
    2.15
    thanks
    2.13
     Critics
    2.13
    lash
    2.10
    among
    2.01
    rovers
    1.96
     uproar
    1.95
    follow
    1.94
    agues
    1.92
    Activations Density 0.521%

    No Known Activations