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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7214
    Prev
    Next
    INDEX
    Explanations

    references to economic and regulatory policies

    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
    0:0.02
    1:0.03
    2:0.04
    3:0.04
    4:0.09
    5:0.03
    6:0.50
    7:0.03
    8:0.04
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
    andise
    -1.61
    indal
    -1.43
    assies
    -1.38
     Emin
    -1.38
     partName
    -1.37
    aucuses
    -1.36
    lees
    -1.33
    rencies
    -1.31
    lycer
    -1.31
    asks
    -1.26
    POSITIVE LOGITS
    ccording
    1.65
    pillar
    1.48
    thin
    1.37
    fifth
    1.37
    dozen
    1.32
    oser
    1.31
    maximum
    1.30
    href
    1.29
    teenth
    1.27
    unch
    1.26
    Activations Density 0.623%

    No Known Activations