© 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. 5-ATT-KK
    6. 28659
    Prev
    Next
    INDEX
    Explanations

    verbs in past tense and related phrases

    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
    0:0.03
    1:0.03
    2:0.12
    3:0.07
    4:0.10
    5:0.04
    6:0.04
    7:0.29
    8:0.03
    9:0.04
    10:0.12
    11:0.06
    Negative Logits
     invented
    -1.65
    龍�
    -1.59
    usage
    -1.53
    iasis
    -1.50
    エル
    -1.49
    oggle
    -1.47
    ategor
    -1.45
    龍
    -1.44
    sometimes
    -1.44
     imaginable
    -1.44
    POSITIVE LOGITS
    semble
    2.23
    semb
    1.70
    mosp
    1.70
     Aires
    1.63
     Lumpur
    1.58
    conference
    1.57
    orate
    1.53
     rehearsal
    1.51
     embassy
    1.50
     colleg
    1.47
    Activations Density 0.000%

    No Known Activations