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. 10-ATT-KK
    6. 14658
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and economic activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.02
    3:0.05
    4:0.04
    5:0.52
    6:0.01
    7:0.02
    8:0.02
    9:0.15
    10:0.01
    11:0.05
    Negative Logits
     [+
    -3.20
     nor
    -3.09
     exceeds
    -2.98
     absence
    -2.78
     excludes
    -2.77
     awaits
    -2.58
     defied
    -2.55
    "]=>
    -2.54
     pending
    -2.44
     refuses
    -2.42
    POSITIVE LOGITS
     again
    5.30
    again
    5.07
     anew
    4.32
    later
    4.13
     Again
    4.04
     shortly
    3.93
     sooner
    3.86
     AGA
    3.85
    instead
    3.83
     REALLY
    3.68
    Activations Density 0.253%

    No Known Activations