Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27588
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms related to computing or technology

    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
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.47
    7:0.03
    8:0.03
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     Croatian
    -1.49
     Finnish
    -1.41
     Norwegian
    -1.36
    velt
    -1.33
     Nikol
    -1.28
     Danish
    -1.20
     terror
    -1.19
     Swedish
    -1.18
     Serbian
    -1.18
    Benz
    -1.17
    POSITIVE LOGITS
    wcs
    1.95
    illin
    1.59
    nown
    1.58
    ciating
    1.51
    arro
    1.49
    γ
    1.45
    ilater
    1.44
    atters
    1.37
    TAG
    1.35
    nces
    1.35
    Activations Density 0.011%

    No Known Activations