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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11354
    Prev
    Next
    INDEX
    Explanations

    references to chocolate products and related recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.35
    1:0.01
    2:0.06
    3:0.12
    4:0.03
    5:0.08
    6:0.05
    7:0.06
    8:0.10
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
    ayson
    -2.60
     Telecommunications
    -2.52
     Dial
    -2.45
     Telecom
    -2.44
     modem
    -2.43
     Technician
    -2.40
     diagn
    -2.35
    orth
    -2.30
    pmwiki
    -2.27
     Nanto
    -2.24
    POSITIVE LOGITS
     chocolate
    5.13
     Chocolate
    4.72
     cookies
    4.72
     cocoa
    4.36
     baked
    4.28
     Cookies
    4.25
    ocolate
    4.23
     Cookie
    4.23
     cookie
    4.23
     dough
    4.18
    Activations Density 0.292%

    No Known Activations