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. 22374
    Prev
    Next
    INDEX
    Explanations

    words related to nanotechnology and materials science, particularly focusing on nanotubes, nanoscale structures, and nanoelectronics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to nanotechnology and nanostructures

    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
    0:0.08
    1:0.04
    2:0.24
    3:0.09
    4:0.13
    5:0.06
    6:0.03
    7:0.04
    8:0.05
    9:0.11
    10:0.06
    11:0.03
    Negative Logits
     Arrows
    -1.33
    ardless
    -1.21
     pagan
    -1.15
     Gospel
    -1.15
     Maced
    -1.11
     Druid
    -1.11
     Fiesta
    -1.10
     Patron
    -1.09
     Tigers
    -1.06
     Painter
    -1.06
    POSITIVE LOGITS
    sand
    1.40
    onductor
    1.39
    orbit
    1.36
    uders
    1.34
    ellery
    1.32
    otech
    1.29
    paces
    1.23
    asher
    1.23
    liv
    1.22
    uries
    1.21
    Activations Density 0.007%

    No Known Activations