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. 14718
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and sacrifice in 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
    0:0.06
    1:0.12
    2:0.19
    3:0.04
    4:0.04
    5:0.02
    6:0.04
    7:0.31
    8:0.02
    9:0.03
    10:0.06
    11:0.03
    Negative Logits
     Fresno
    -1.97
     Blanc
    -1.86
     nineteenth
    -1.82
     cheering
    -1.80
    fo
    -1.79
    erey
    -1.77
    eenth
    -1.76
    arf
    -1.74
     protested
    -1.72
     Falk
    -1.71
    POSITIVE LOGITS
    cknow
    1.97
    odon
    1.95
    ˜
    1.86
    CDC
    1.84
     designers
    1.83
    ody
    1.81
     Design
    1.80
    OTOS
    1.79
    otom
    1.79
     Detect
    1.79
    Activations Density 0.017%

    No Known Activations