© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10999
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or keywords that indicate emphasis or importance in a document

    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
    0:0.55
    1:0.02
    2:0.04
    3:0.02
    4:0.06
    5:0.02
    6:0.06
    7:0.03
    8:0.03
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
    �
    -2.03
     acknow
    -1.88
     Citation
    -1.88
     namely
    -1.75
     Discuss
    -1.75
    ャ
    -1.68
    ategory
    -1.67
     ��������
    -1.66
    hement
    -1.66
     Whereas
    -1.65
    POSITIVE LOGITS
    idine
    1.82
    pedia
    1.74
    stice
    1.73
    kind
    1.67
    dit
    1.66
    til
    1.63
    gain
    1.63
    apor
    1.61
    efer
    1.60
    iddler
    1.60
    Activations Density 0.229%

    No Known Activations