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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10571
    Prev
    Next
    INDEX
    Explanations

    details regarding political polls and public opinion

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.03
    4:0.06
    5:0.02
    6:0.23
    7:0.04
    8:0.10
    9:0.28
    10:0.02
    11:0.06
    Negative Logits
     Sloven
    -4.75
    č
    -4.36
     Yugoslav
    -3.77
     Nikola
    -3.71
    Socket
    -3.71
     Sok
    -3.67
    ript
    -3.61
     msg
    -3.60
    Lat
    -3.59
    Georg
    -3.59
    POSITIVE LOGITS
     Harper
    11.28
    Har
    6.97
     Mulcair
    5.40
     Duffy
    4.91
     Baird
    4.79
     Trudeau
    4.79
     Conservatives
    4.66
     Conservative
    4.62
     Barrett
    4.57
     Ottawa
    4.49
    Activations Density 0.008%

    No Known Activations