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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22279
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and cybersecurity solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.12
    2:0.04
    3:0.07
    4:0.03
    5:0.06
    6:0.07
    7:0.13
    8:0.04
    9:0.07
    10:0.18
    11:0.08
    Negative Logits
     Myster
    -1.54
     Bastard
    -1.45
     Murder
    -1.40
     drunken
    -1.39
     Tears
    -1.37
     Weird
    -1.36
     traitor
    -1.35
     prank
    -1.35
    Strange
    -1.35
     coward
    -1.33
    POSITIVE LOGITS
    izons
    1.65
     leveraging
    1.63
     complementary
    1.55
     innovative
    1.51
     sustainability
    1.48
     technologies
    1.48
     globally
    1.47
     frameworks
    1.47
     workforce
    1.46
     efficiently
    1.45
    Activations Density 0.640%

    No Known Activations