© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    quotations surrounded by single quotation marks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quoted statements or phrases

    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
    0:0.07
    1:0.07
    2:0.05
    3:0.04
    4:0.28
    5:0.09
    6:0.13
    7:0.05
    8:0.05
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
     favour
    -1.81
    stood
    -1.67
    soDeliveryDate
    -1.63
     forgetting
    -1.62
     favor
    -1.52
    hler
    -1.51
    sylv
    -1.49
     kind
    -1.42
     adm
    -1.41
    yan
    -1.40
    POSITIVE LOGITS
    quartered
    1.97
    ideshow
    1.54
     Mehran
    1.50
    ...]
    1.49
     Prot
    1.47
     Photos
    1.46
     Timeline
    1.45
    Mot
    1.43
    itans
    1.42
    AUT
    1.40
    Activations Density 0.001%

    No Known Activations