© 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. 43552
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting related to set theory and cardinality

    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
    0:0.13
    1:0.12
    2:0.07
    3:0.07
    4:0.05
    5:0.11
    6:0.05
    7:0.03
    8:0.12
    9:0.06
    10:0.06
    11:0.07
    Negative Logits
    uador
    -1.68
    ê
    -1.62
    kie
    -1.55
    ague
    -1.54
    aith
    -1.54
    plets
    -1.54
    antics
    -1.52
    Reviewer
    -1.52
    hig
    -1.47
    icking
    -1.46
    POSITIVE LOGITS
     gum
    1.51
     base
    1.50
     shaft
    1.50
     divided
    1.46
     divid
    1.44
     transpl
    1.44
     shrink
    1.38
     multiplied
    1.37
     unprotected
    1.35
     Base
    1.34
    Activations Density 0.007%

    No Known Activations