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. 8454
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to health, technology, and societal issues

    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
    0:0.03
    1:0.10
    2:0.10
    3:0.03
    4:0.03
    5:0.03
    6:0.09
    7:0.06
    8:0.27
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    qqa
    -1.43
    avage
    -1.39
    fty
    -1.32
    azor
    -1.32
    imester
    -1.32
    ube
    -1.32
    utterstock
    -1.31
    hement
    -1.31
    cpp
    -1.30
    >:
    -1.28
    POSITIVE LOGITS
     Rig
    1.35
     privileged
    1.32
     conform
    1.30
     cop
    1.28
     wont
    1.27
     plays
    1.22
     works
    1.18
     intersect
    1.17
     Lie
    1.15
    Lie
    1.11
    Activations Density 0.092%

    No Known Activations