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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 1-ATT-KK
    6. 6421
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.03
    2:0.04
    3:0.01
    4:0.05
    5:0.39
    6:0.05
    7:0.09
    8:0.03
    9:0.03
    10:0.03
    11:0.14
    Negative Logits
    fo
    -1.77
    eah
    -1.75
    hene
    -1.72
    ordes
    -1.71
    BRE
    -1.65
    dra
    -1.62
    dri
    -1.61
    psc
    -1.60
    gra
    -1.60
    mun
    -1.59
    POSITIVE LOGITS
    staking
    1.56
     recovers
    1.55
    ��
    1.52
     populations
    1.50
     repaid
    1.49
     balances
    1.48
     lessons
    1.47
     counterpart
    1.47
     subsidies
    1.45
     unforeseen
    1.42
    Activations Density 0.111%

    No Known Activations