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. 7-ATT-KK
    6. 9342
    Prev
    Next
    INDEX
    Explanations

    references to legal and financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.33
    1:0.04
    2:0.02
    3:0.05
    4:0.04
    5:0.06
    6:0.04
    7:0.02
    8:0.28
    9:0.05
    10:0.02
    11:0.01
    Negative Logits
    uncture
    -1.77
    ometimes
    -1.57
     wearer
    -1.54
     consume
    -1.54
     lasted
    -1.52
     vaping
    -1.51
     unpredict
    -1.51
     raining
    -1.50
     Slightly
    -1.49
     circumference
    -1.47
    POSITIVE LOGITS
     affidav
    2.11
     affidavit
    2.00
    idav
    1.88
     Statement
    1.88
     memorandum
    1.84
     filings
    1.83
    Charges
    1.79
    Letter
    1.79
     Securities
    1.77
     securities
    1.75
    Activations Density 0.012%

    No Known Activations