Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 133
    Prev
    Next
    INDEX
    Explanations

    references to political candidacies and elections

    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
    2:0.07
    3:0.20
    4:0.02
    5:0.15
    6:0.02
    7:0.06
    8:0.05
    9:0.01
    10:0.28
    11:0.02
    Negative Logits
     brill
    -2.04
    details
    -2.01
     unfold
    -1.99
     playbook
    -1.90
    toc
    -1.89
     unfolds
    -1.85
    ipers
    -1.83
    dos
    -1.75
     manuals
    -1.75
     sophistication
    -1.73
    POSITIVE LOGITS
     concurrently
    2.19
     someday
    1.96
     differently
    1.95
    bernatorial
    1.90
    iatrics
    1.82
    ARB
    1.81
     2024
    1.81
     Legislative
    1.75
     again
    1.75
     respectively
    1.74
    Activations Density 0.140%

    No Known Activations