© 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. 20986
    Prev
    Next
    INDEX
    Explanations

    phrases indicating moderate or weak assessments of truth and reliability

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.03
    4:0.10
    5:0.04
    6:0.02
    7:0.05
    8:0.02
    9:0.31
    10:0.02
    11:0.24
    Negative Logits
    agents
    -2.56
     Beasts
    -2.26
     sessions
    -2.22
     superv
    -2.20
     outfits
    -2.19
    devices
    -2.16
     entrants
    -2.09
    ovie
    -2.08
    wives
    -2.06
    rams
    -2.06
    POSITIVE LOGITS
     diminished
    3.24
     negligible
    3.07
     limited
    2.90
     waning
    2.86
    limited
    2.70
    existent
    2.67
     heightened
    2.63
     disadvantage
    2.62
     constrained
    2.61
     durability
    2.58
    Activations Density 0.126%

    No Known Activations