© 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. 5-ATT-KK
    11. 6292
    Prev
    Next
    INDEX
    Explanations

    instances where events or experiences are abruptly interrupted or ended prematurely

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.10
    3:0.08
    4:0.25
    5:0.03
    6:0.03
    7:0.20
    8:0.04
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    soType
    -1.53
     fir
    -1.50
    evidence
    -1.41
     applied
    -1.39
    paralle
    -1.34
    sbm
    -1.33
     cous
    -1.31
     upside
    -1.31
    ensed
    -1.29
    itle
    -1.26
    POSITIVE LOGITS
    Interstitial
    1.57
    rontal
    1.40
    Skip
    1.39
     prematurely
    1.37
    eches
    1.29
    loading
    1.29
     Cheong
    1.28
     phil
    1.26
    adelphia
    1.26
    mph
    1.26
    Activations Density 0.001%

    No Known Activations