© 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. 43868
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or comparisons

    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
    2:0.11
    3:0.06
    4:0.23
    5:0.03
    6:0.14
    7:0.14
    8:0.03
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     accessed
    -1.42
     Units
    -1.35
     Attacks
    -1.32
     Females
    -1.31
     Males
    -1.31
     assembled
    -1.29
     ALSO
    -1.28
    guards
    -1.27
     Cells
    -1.25
    rium
    -1.23
    POSITIVE LOGITS
     convinc
    1.65
    enough
    1.54
    henko
    1.54
    ensical
    1.52
    BuyableInstoreAndOnline
    1.51
    ibaba
    1.44
    successfully
    1.44
    agra
    1.40
    ingen
    1.39
     satisf
    1.38
    Activations Density 0.011%

    No Known Activations