© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43835
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and associated phrases indicating states or actions

    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
    2:0.08
    3:0.14
    4:0.06
    5:0.02
    6:0.29
    7:0.05
    8:0.04
    9:0.04
    10:0.10
    11:0.09
    Negative Logits
    ween
    -1.37
    reated
    -1.35
    oxic
    -1.24
     appet
    -1.22
    chery
    -1.20
    abase
    -1.15
    gas
    -1.15
    uras
    -1.15
    ashtra
    -1.15
    acket
    -1.14
    POSITIVE LOGITS
    llor
    1.57
    CV
    1.42
     ende
    1.41
    morrow
    1.33
    osen
    1.33
     hereafter
    1.32
    Reviewed
    1.29
    dal
    1.29
     NX
    1.26
    bern
    1.25
    Activations Density 0.024%

    No Known Activations