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. 8390
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns or names, particularly those related to people or places

    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
    1:0.03
    2:0.09
    3:0.30
    4:0.03
    5:0.03
    6:0.12
    7:0.07
    8:0.05
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
     fodder
    -1.13
     baptism
    -1.12
     Adin
    -1.06
     abundantly
    -1.06
     acknow
    -1.03
     laundry
    -1.03
     CPR
    -1.02
     inver
    -1.02
     corp
    -1.02
     knees
    -1.01
    POSITIVE LOGITS
    ipel
    1.47
    ICT
    1.37
    oxide
    1.28
    nels
    1.27
    gage
    1.26
    idges
    1.22
    oqu
    1.22
    INAL
    1.20
    awks
    1.20
    leans
    1.18
    Activations Density 0.007%

    No Known Activations