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. 9587
    Prev
    Next
    INDEX
    Explanations

    elements of social discourse and activism

    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
    0:0.33
    1:0.05
    2:0.03
    3:0.08
    4:0.03
    5:0.12
    6:0.04
    7:0.02
    8:0.14
    9:0.08
    10:0.01
    11:0.01
    Negative Logits
    uncture
    -1.84
     Shutterstock
    -1.75
    angering
    -1.75
    aples
    -1.70
     suburb
    -1.62
    Db
    -1.62
     distances
    -1.59
    urus
    -1.58
     Compare
    -1.57
    ecause
    -1.55
    POSITIVE LOGITS
     proposals
    2.16
     retrospective
    1.95
     substantive
    1.92
     proposal
    1.91
     ideas
    1.85
     compelling
    1.83
     concepts
    1.79
     definitive
    1.78
     nominees
    1.75
     groundbreaking
    1.75
    Activations Density 0.007%

    No Known Activations