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. 20679
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to character relationships and developments 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
    0:0.05
    1:0.01
    2:0.08
    3:0.33
    4:0.03
    5:0.13
    6:0.01
    7:0.08
    8:0.04
    9:0.01
    10:0.14
    11:0.02
    Negative Logits
     Recommend
    -2.45
    Recommend
    -2.34
     Citation
    -2.30
     ))
    -2.30
    ))
    -2.30
    )))
    -2.29
     Logo
    -2.25
     Included
    -2.25
     Added
    -2.19
    )).
    -2.19
    POSITIVE LOGITS
     detective
    2.67
     apprentice
    2.58
     estranged
    2.51
     rebellious
    2.39
     struggles
    2.38
     daring
    2.36
     protagonist
    2.35
     befriend
    2.35
     patriarch
    2.35
     kidnapped
    2.34
    Activations Density 0.914%

    No Known Activations