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. 3-ATT-KK
    6. 8556
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or change of location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.17
    3:0.14
    4:0.02
    5:0.02
    6:0.05
    7:0.12
    8:0.05
    9:0.06
    10:0.09
    11:0.19
    Negative Logits
    oshenko
    -1.21
    anium
    -1.18
    urnal
    -1.02
    ariat
    -1.00
    Vision
    -1.00
    vre
    -0.97
    ments
    -0.95
     weave
    -0.94
    Meg
    -0.94
     sphere
    -0.94
    POSITIVE LOGITS
    gently
    1.03
     landsl
    0.94
     refurb
    0.94
     reminders
    0.93
     rejuven
    0.91
    cffffcc
    0.91
     ObamaCare
    0.90
    again
    0.89
    fal
    0.89
    =]
    0.89
    Activations Density 0.006%

    No Known Activations