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. 8496
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and other specific prepositions indicating location or context

    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
    0:0.02
    1:0.02
    2:0.17
    3:0.19
    4:0.02
    5:0.03
    6:0.05
    7:0.10
    8:0.11
    9:0.06
    10:0.09
    11:0.09
    Negative Logits
    ufact
    -1.58
     Cly
    -1.11
    utive
    -1.10
    arton
    -1.10
    anship
    -1.09
    ajor
    -1.07
    ihad
    -1.07
    pees
    -1.06
    vised
    -1.04
    ospons
    -1.03
    POSITIVE LOGITS
    rontal
    1.06
     injust
    1.05
     blurry
    1.05
     cruc
    1.05
    �
    1.03
     arrog
    1.00
    Invalid
    0.99
     indist
    0.99
     tsun
    0.99
     pointless
    0.98
    Activations Density 0.023%

    No Known Activations