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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10438
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.07
    2:0.18
    3:0.08
    4:0.01
    5:0.04
    6:0.07
    7:0.08
    8:0.18
    9:0.05
    10:0.10
    11:0.08
    Negative Logits
    vik
    -1.38
    vised
    -1.18
    rupted
    -1.08
    alled
    -1.03
    uctions
    -0.96
    icho
    -0.95
    istries
    -0.95
    ussed
    -0.95
    ño
    -0.94
    ivated
    -0.94
    POSITIVE LOGITS
    equality
    1.17
    dies
    1.01
    yip
    1.00
    inventoryQuantity
    1.00
    Average
    0.97
     predecessors
    0.97
     regards
    0.96
    Ctrl
    0.92
     averages
    0.91
     rivals
    0.90
    Activations Density 0.094%

    No Known Activations