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. 1-ATT-KK
    6. 6301
    Prev
    Next
    INDEX
    Explanations

    mentions of films or movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.04
    2:0.03
    3:0.02
    4:0.04
    5:0.04
    6:0.37
    7:0.04
    8:0.03
    9:0.03
    10:0.02
    11:0.10
    Negative Logits
     maturity
    -1.52
     refuel
    -1.52
    onis
    -1.51
     Kamp
    -1.47
     leveling
    -1.45
     braking
    -1.45
     theory
    -1.45
    Args
    -1.44
     reasoning
    -1.42
     drilled
    -1.41
    POSITIVE LOGITS
    obook
    2.48
    ヘラ
    1.95
    DragonMagazine
    1.94
    conservancy
    1.93
    phans
    1.79
    edom
    1.76
     Advertisement
    1.76
    IFF
    1.72
    artisan
    1.68
    Title
    1.64
    Activations Density 0.001%

    No Known Activations