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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27521
    Prev
    Next
    INDEX
    Explanations

    phrases indicating voter turnout and participation levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.09
    3:0.05
    4:0.18
    5:0.02
    6:0.07
    7:0.33
    8:0.02
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    opa
    -1.54
    rag
    -1.54
     Cutter
    -1.51
     dangling
    -1.45
    igure
    -1.45
     ashes
    -1.42
     predecessor
    -1.41
    agall
    -1.41
    milo
    -1.41
    uliffe
    -1.41
    POSITIVE LOGITS
    naires
    1.58
     Chinatown
    1.57
    cmp
    1.47
     HuffPost
    1.42
     Contest
    1.40
     Bangkok
    1.39
     Calais
    1.35
     caucuses
    1.34
     surpr
    1.33
     booths
    1.33
    Activations Density 0.004%

    No Known Activations