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. 5-ATT-KK
    6. 7159
    Prev
    Next
    INDEX
    Explanations

    conditional statements regarding policies or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.06
    3:0.08
    4:0.05
    5:0.12
    6:0.05
    7:0.03
    8:0.05
    9:0.05
    10:0.13
    11:0.27
    Negative Logits
    lined
    -1.53
     Hirosh
    -1.37
    ‑
    -1.37
     encl
    -1.37
    ways
    -1.36
     occupancy
    -1.36
     routers
    -1.31
     corridors
    -1.31
     patents
    -1.30
    liners
    -1.29
    POSITIVE LOGITS
    wcsstore
    1.82
    catentry
    1.53
    Friends
    1.51
    ocious
    1.50
    dose
    1.49
     Flavoring
    1.47
     relapse
    1.46
    AppData
    1.43
    ebook
    1.43
     vomiting
    1.43
    Activations Density 0.068%

    No Known Activations