© 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. 5-ATT-KK
    11. 41465
    Prev
    Next
    INDEX
    Explanations

    references to financial issues and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.20
    3:0.05
    4:0.31
    5:0.03
    6:0.03
    7:0.10
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    aucuses
    -1.58
     Horses
    -1.54
    Hum
    -1.48
    quickShipAvailable
    -1.46
    SPONSORED
    -1.45
    irs
    -1.45
    brids
    -1.44
     Houses
    -1.39
    usions
    -1.37
    esters
    -1.37
    POSITIVE LOGITS
     accordingly
    1.87
     nonetheless
    1.64
     depends
    1.36
     nevertheless
    1.36
     multiplier
    1.34
     thus
    1.29
     affair
    1.28
     attracting
    1.25
    Aid
    1.25
     hence
    1.24
    Activations Density 0.002%

    No Known Activations