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. 7-ATT-KK
    6. 18951
    Prev
    Next
    INDEX
    Explanations

    the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.09
    4:0.07
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    itual
    -2.50
    enge
    -2.32
    sam
    -2.23
    gra
    -2.22
    nian
    -2.20
    sen
    -2.16
    umatic
    -2.13
    disciplinary
    -2.13
    paren
    -2.11
    bard
    -2.03
    POSITIVE LOGITS
     refunds
    2.28
     refund
    2.14
     LTE
    2.13
     nonexistent
    2.08
     Sync
    2.04
    osterone
    2.00
     rebuild
    1.95
     faire
    1.90
     revenue
    1.88
     profits
    1.88
    Activations Density 0.000%

    No Known Activations