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. 7713
    Prev
    Next
    INDEX
    Explanations

    references to narrative structure and its elements in storytelling

    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
    0:0.03
    1:0.01
    2:0.03
    3:0.17
    4:0.02
    5:0.03
    6:0.02
    7:0.03
    8:0.02
    9:0.01
    10:0.56
    11:0.01
    Negative Logits
    izons
    -1.69
    Website
    -1.68
     incumb
    -1.63
    izens
    -1.61
    planet
    -1.59
     Yorkers
    -1.57
     Telesc
    -1.56
     Converted
    -1.51
     billionaires
    -1.49
    iens
    -1.49
    POSITIVE LOGITS
     manner
    2.72
     vicinity
    2.35
     context
    2.31
     case
    2.28
     contexts
    2.21
     respects
    2.18
    soDeliveryDate
    2.17
     fashion
    2.14
     guise
    2.11
     aftermath
    2.11
    Activations Density 1.600%

    No Known Activations