© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8615
    Prev
    Next
    INDEX
    Explanations

    references to limits and constraints in various contexts, particularly in relation to debt, energy, and water

    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
    1:0.21
    2:0.07
    3:0.04
    4:0.06
    5:0.01
    6:0.11
    7:0.15
    8:0.02
    9:0.03
    10:0.04
    11:0.14
    Negative Logits
     Maid
    -2.20
     Herz
    -2.15
     Rough
    -2.11
     Purple
    -2.10
    seys
    -2.09
     Rowe
    -2.07
    solid
    -2.07
    usted
    -2.05
    obal
    -2.04
     Secondary
    -2.02
    POSITIVE LOGITS
     limits
    5.85
     limit
    5.57
     Limits
    4.93
    Limit
    4.90
     Limit
    4.65
     limitation
    4.63
    limit
    4.57
     limitations
    4.48
    limits
    4.47
     restriction
    4.46
    Activations Density 0.036%

    No Known Activations