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. 9-ATT-KK
    6. 20692
    Prev
    Next
    INDEX
    Explanations

    references to the Salt Lake Tribune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.07
    3:0.05
    4:0.05
    5:0.06
    6:0.11
    7:0.06
    8:0.05
    9:0.28
    10:0.06
    11:0.06
    Negative Logits
    andre
    -3.26
     Jung
    -3.21
     Nero
    -3.15
    NG
    -3.08
     Bib
    -3.06
     Bud
    -2.99
     Glob
    -2.96
     Advertisement
    -2.94
     Dem
    -2.91
    AD
    -2.89
    POSITIVE LOGITS
     Lake
    3.68
    Lake
    3.40
    lake
    3.38
     Leah
    3.38
     Allaah
    3.24
    Salt
    3.12
     Lav
    3.08
     lake
    3.06
    arl
    3.03
    KT
    2.96
    Activations Density 0.000%

    No Known Activations