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. 10059
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes and colors

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.07
    4:0.04
    5:0.06
    6:0.14
    7:0.27
    8:0.06
    9:0.02
    10:0.11
    11:0.08
    Negative Logits
    Privacy
    -1.17
    perty
    -1.10
    untled
    -1.08
    cffff
    -1.01
     patience
    -1.01
     proactive
    -0.97
    sers
    -0.97
     hindsight
    -0.97
    ItemTracker
    -0.96
    ETHOD
    -0.95
    POSITIVE LOGITS
     blot
    1.12
    č
    1.10
    chev
    1.09
     denote
    1.08
    leon
    1.05
     stripes
    1.03
    oxide
    1.01
     matte
    1.00
    apple
    1.00
     denotes
    0.99
    Activations Density 0.122%

    No Known Activations