© 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. 46157
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week and their significance in the context of events

    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
    0:0.16
    1:0.04
    2:0.10
    3:0.03
    4:0.05
    5:0.05
    6:0.05
    7:0.02
    8:0.15
    9:0.05
    10:0.10
    11:0.13
    Negative Logits
     HOUSE
    -1.35
    zik
    -1.35
    jah
    -1.29
    emphasis
    -1.28
    claimer
    -1.25
    DEF
    -1.24
    aed
    -1.23
     Fraud
    -1.23
    ded
    -1.21
     Wage
    -1.21
    POSITIVE LOGITS
    Interstitial
    1.93
    ember
    1.80
     respectively
    1.65
    ADVERTISEMENT
    1.39
    ―
    1.33
    ilaterally
    1.32
    →
    1.32
     etc
    1.31
     depending
    1.28
    thinkable
    1.28
    Activations Density 0.012%

    No Known Activations