© 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. 10452
    Prev
    Next
    INDEX
    Explanations

    terms associated with financial risk and advantage

    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
    1:0.04
    2:0.03
    3:0.04
    4:0.08
    5:0.03
    6:0.03
    7:0.05
    8:0.01
    9:0.19
    10:0.03
    11:0.38
    Negative Logits
     batches
    -2.48
     iterations
    -2.46
    uphem
    -2.33
     snippets
    -2.24
     statutes
    -2.21
     phrases
    -2.17
     Acts
    -2.16
     Examples
    -2.15
     stories
    -2.12
     procedures
    -2.10
    POSITIVE LOGITS
     disadvantage
    3.10
     position
    2.65
     importance
    2.35
     edge
    2.31
     forefront
    2.29
     detriment
    2.25
     plateau
    2.25
     susceptibility
    2.23
     mercy
    2.18
     difficulty
    2.16
    Activations Density 0.011%

    No Known Activations