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. 7-ATT-KK
    6. 9336
    Prev
    Next
    INDEX
    Explanations

    references to images and their credits in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.02
    3:0.05
    4:0.05
    5:0.39
    6:0.06
    7:0.02
    8:0.11
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
     chores
    -2.28
     scheduling
    -2.27
     abst
    -2.20
     urgent
    -2.18
     worrisome
    -2.13
    entimes
    -2.12
     stren
    -2.07
     disagreements
    -2.04
    cffffcc
    -2.04
     affairs
    -2.03
    POSITIVE LOGITS
     Flickr
    3.14
     Photographer
    2.85
     Shutterstock
    2.60
     Photography
    2.56
    photos
    2.46
    ylan
    2.41
     photographer
    2.37
     Photograph
    2.37
    Photos
    2.36
     Thumbnails
    2.35
    Activations Density 0.076%

    No Known Activations