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. 3-ATT-KK
    6. 7840
    Prev
    Next
    INDEX
    Explanations

    instances of parenthetical punctuation

    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
    0:0.07
    1:0.23
    2:0.06
    3:0.01
    4:0.04
    5:0.09
    6:0.05
    7:0.06
    8:0.08
    9:0.10
    10:0.09
    11:0.06
    Negative Logits
     hinges
    -1.51
    aceae
    -1.42
    ¶
    -1.36
     robbers
    -1.36
     balloon
    -1.31
     governs
    -1.27
     Hearts
    -1.23
     margins
    -1.23
     orderly
    -1.22
     wills
    -1.22
    POSITIVE LOGITS
    wp
    1.70
    weet
    1.62
    np
    1.52
    ysc
    1.50
    RG
    1.50
    CBC
    1.50
    biz
    1.46
    Brend
    1.45
    )</
    1.44
    FY
    1.43
    Activations Density 0.014%

    No Known Activations