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. 5-ATT-KK
    6. 7191
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance and quality in regulatory contexts

    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
    0:0.02
    1:0.01
    2:0.17
    3:0.28
    4:0.10
    5:0.04
    6:0.03
    7:0.06
    8:0.05
    9:0.05
    10:0.08
    11:0.06
    Negative Logits
     Cheong
    -1.66
    uphem
    -1.60
    asel
    -1.57
    ayne
    -1.52
    aiden
    -1.49
     lately
    -1.46
     likened
    -1.45
    ext
    -1.43
     apostles
    -1.41
     cousins
    -1.40
    POSITIVE LOGITS
     responsibly
    1.74
     safely
    1.67
    ularity
    1.60
     compliant
    1.58
     properly
    1.57
     safe
    1.54
     future
    1.52
    ンジ
    1.52
    vironment
    1.51
    inate
    1.49
    Activations Density 0.161%

    No Known Activations