© 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. 3-ATT-KK
    11. 7538
    Prev
    Next
    INDEX
    Explanations

    statements that emphasize existence or condition, particularly those involving the verb "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.06
    2:0.05
    3:0.03
    4:0.03
    5:0.16
    6:0.08
    7:0.06
    8:0.08
    9:0.07
    10:0.08
    11:0.20
    Negative Logits
     logs
    -1.70
    ensor
    -1.69
     authorised
    -1.60
     consent
    -1.54
    elaide
    -1.52
     rented
    -1.52
     Register
    -1.50
     Siberian
    -1.50
     registry
    -1.49
     Dept
    -1.49
    POSITIVE LOGITS
    ozy
    2.03
     Firstly
    1.88
    ASY
    1.88
    ndra
    1.81
    BIP
    1.75
    natureconservancy
    1.72
    Reviewer
    1.69
    WARE
    1.69
     Flavoring
    1.69
    gey
    1.66
    Activations Density 0.111%

    No Known Activations