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. 1-ATT-KK
    6. 6399
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.10
    2:0.06
    3:0.05
    4:0.07
    5:0.09
    6:0.08
    7:0.08
    8:0.06
    9:0.05
    10:0.06
    11:0.12
    Negative Logits
     respectively
    -1.76
     engine
    -1.57
     payload
    -1.56
     airspace
    -1.54
     Terminal
    -1.51
     engines
    -1.47
     coastline
    -1.46
     Goods
    -1.46
    Mobil
    -1.46
     perimeter
    -1.45
    POSITIVE LOGITS
    actionDate
    2.48
     largeDownload
    1.76
    quickShipAvailable
    1.69
    essors
    1.69
    azing
    1.56
    inness
    1.56
    phasis
    1.55
    VIDIA
    1.54
    utterstock
    1.53
    nutrition
    1.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.