© 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. 43818
    Prev
    Next
    INDEX
    Explanations

    numeric representations or numerical data within text

    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
    0:0.04
    1:0.02
    2:0.10
    3:0.04
    4:0.05
    5:0.03
    6:0.21
    7:0.04
    8:0.07
    9:0.05
    10:0.13
    11:0.16
    Negative Logits
     Bahamas
    -1.29
     Anonymous
    -1.25
     Lancet
    -1.21
     Rousse
    -1.18
     retract
    -1.15
     bladder
    -1.15
     Cannes
    -1.08
    FIL
    -1.07
     unidentified
    -1.07
     Satanic
    -1.05
    POSITIVE LOGITS
    itect
    1.77
    ritis
    1.58
    oy
    1.49
    brew
    1.45
    hyde
    1.39
    olate
    1.37
    uild
    1.36
    ocations
    1.33
    Downloadha
    1.30
    uilt
    1.29
    Activations Density 0.003%

    No Known Activations