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. 6416
    Prev
    Next
    INDEX
    Explanations

    phrases related to compliance with regulations or laws

    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
    0:0.39
    1:0.09
    2:0.03
    3:0.02
    4:0.05
    5:0.06
    6:0.10
    7:0.05
    8:0.02
    9:0.02
    10:0.02
    11:0.10
    Negative Logits
    pload
    -1.71
     Plays
    -1.63
    naissance
    -1.63
    assic
    -1.52
    uni
    -1.52
    nova
    -1.51
    xiety
    -1.47
    inav
    -1.42
    spot
    -1.41
    heastern
    -1.40
    POSITIVE LOGITS
     thereto
    1.83
     ACTIONS
    1.76
     standards
    1.74
     rules
    1.71
     terms
    1.66
    EMA
    1.57
     Rule
    1.55
     rule
    1.53
     standard
    1.49
    う
    1.48
    Activations Density 0.012%

    No Known Activations