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. 8575
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate reports, lawsuits, or official communications

    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
    0:0.01
    1:0.13
    2:0.10
    3:0.17
    4:0.01
    5:0.03
    6:0.06
    7:0.10
    8:0.09
    9:0.05
    10:0.09
    11:0.08
    Negative Logits
    achev
    -1.50
    ��
    -1.38
    assies
    -1.24
    bye
    -1.22
    utical
    -1.22
    termin
    -1.18
    dule
    -1.16
    akeru
    -1.15
    ouver
    -1.10
    unction
    -1.07
    POSITIVE LOGITS
     author
    1.15
     authors
    1.14
     citation
    1.09
     Popular
    1.09
     applicable
    1.06
     quoted
    1.04
     citations
    1.04
     eyewitness
    1.03
     published
    1.00
     Parables
    1.00
    Activations Density 0.015%

    No Known Activations