© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20155
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculation and uncertainty concerning claims and statements

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.04
    4:0.11
    5:0.12
    6:0.03
    7:0.04
    8:0.02
    9:0.39
    10:0.02
    11:0.09
    Negative Logits
     actionGroup
    -2.86
    Join
    -2.70
     workspace
    -2.59
     stocking
    -2.54
     busiest
    -2.36
     downtime
    -2.35
     hosting
    -2.32
     partnership
    -2.28
    heast
    -2.27
     "$:/
    -2.21
    POSITIVE LOGITS
     conjecture
    4.21
     contradicted
    4.04
     conject
    3.93
     assertions
    3.92
     refuted
    3.89
     falsehood
    3.67
     untrue
    3.67
     erroneous
    3.67
     assertion
    3.59
    proven
    3.58
    Activations Density 0.841%

    No Known Activations