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. 10-ATT-KK
    6. 14659
    Prev
    Next
    INDEX
    Explanations

    instances of contrasting perspectives or characterizations within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.09
    5:0.04
    6:0.03
    7:0.05
    8:0.02
    9:0.19
    10:0.02
    11:0.43
    Negative Logits
    leneck
    -2.05
    anned
    -2.00
     landowners
    -2.00
     stash
    -1.96
    ochet
    -1.88
     Founders
    -1.87
    cler
    -1.86
     backlog
    -1.86
    angler
    -1.83
     throats
    -1.83
    POSITIVE LOGITS
     manner
    4.16
     ways
    4.07
     way
    3.56
     terms
    3.52
     sense
    3.43
     fashion
    3.29
     guise
    3.23
     WAY
    3.13
     respects
    2.95
    fashion
    2.83
    Activations Density 0.154%

    No Known Activations