Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44321
    Prev
    Next
    INDEX
    Explanations

    specific years and their relevance in a timeline of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.23
    1:0.17
    2:0.04
    3:0.05
    4:0.02
    5:0.18
    6:0.04
    7:0.01
    8:0.05
    9:0.07
    10:0.06
    11:0.04
    Negative Logits
     eleph
    -1.68
    ↵ 
    -1.56
     orc
    -1.56
     Invisible
    -1.54
     plural
    -1.54
     gorilla
    -1.53
     aster
    -1.50
    igmat
    -1.48
     evenly
    -1.45
    .�
    -1.43
    POSITIVE LOGITS
    ascript
    2.02
    ْ
    1.95
    via
    1.92
    Attempts
    1.85
    --+
    1.83
    aea
    1.74
    -
    1.73
    cember
    1.68
    Aug
    1.67
    thumbnails
    1.67
    Activations Density 0.002%

    No Known Activations