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. 7398
    Prev
    Next
    INDEX
    Explanations

    calls to action or prompts to click for more information

    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
    0:0.02
    1:0.02
    2:0.04
    3:0.08
    4:0.07
    5:0.03
    6:0.32
    7:0.08
    8:0.03
    9:0.05
    10:0.08
    11:0.11
    Negative Logits
    opausal
    -1.28
     purposes
    -1.16
    inguished
    -1.16
    ufact
    -1.12
    icable
    -1.10
     representation
    -1.10
     comprise
    -1.08
     sole
    -1.08
    clerosis
    -1.07
     duties
    -1.07
    POSITIVE LOGITS
     Refresh
    1.51
    bye
    1.29
    ��
    1.24
     comma
    1.20
     sidx
    1.19
     dice
    1.18
    witz
    1.17
    Else
    1.16
     Rebels
    1.13
    Quotes
    1.12
    Activations Density 0.007%

    No Known Activations