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. 9269
    Prev
    Next
    INDEX
    Explanations

    references to forms or applications in a procedural context

    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
    1:0.04
    2:0.01
    3:0.07
    4:0.04
    5:0.12
    6:0.07
    7:0.03
    8:0.35
    9:0.09
    10:0.01
    11:0.01
    Negative Logits
    ovie
    -1.77
     awe
    -1.71
     Watching
    -1.69
     priceless
    -1.68
     Kore
    -1.67
     admiration
    -1.65
     sqor
    -1.64
     Scenes
    -1.63
     admire
    -1.62
     praise
    -1.60
    POSITIVE LOGITS
    Application
    1.87
     registration
    1.85
    Registration
    1.72
     "{
    1.68
     Registration
    1.68
    wrapper
    1.67
    Applications
    1.67
     Forms
    1.67
    handler
    1.65
    iquette
    1.64
    Activations Density 0.004%

    No Known Activations