© 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. 6709
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to individuals or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.05
    1:0.37
    2:0.04
    3:0.04
    4:0.04
    5:0.16
    6:0.04
    7:0.03
    8:0.05
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
    ال
    -1.88
    DATA
    -1.72
    modules
    -1.66
    letter
    -1.65
    tail
    -1.62
    letters
    -1.62
    FTWARE
    -1.62
    friends
    -1.60
    CLASSIFIED
    -1.58
    rossover
    -1.57
    POSITIVE LOGITS
    ich
    2.35
    och
    2.19
    iche
    2.12
    ache
    2.02
    ICH
    2.01
     Ich
    1.87
     Loch
    1.85
    icht
    1.84
    cious
    1.81
    cheat
    1.78
    Activations Density 0.000%

    No Known Activations