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. 2857
    Prev
    Next
    INDEX
    Explanations

    references to legal penalties and punishments

    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
    0:0.04
    1:0.02
    2:0.11
    3:0.09
    4:0.08
    5:0.04
    6:0.04
    7:0.11
    8:0.08
    9:0.04
    10:0.14
    11:0.16
    Negative Logits
    estone
    -1.23
    terday
    -1.22
    got
    -1.19
    winner
    -1.19
    eworks
    -1.17
    fix
    -1.17
    estones
    -1.16
     kindly
    -1.13
    fixes
    -1.11
    ****************
    -1.11
    POSITIVE LOGITS
     depending
    1.37
     Ibid
    1.28
     whichever
    1.25
     endif
    1.21
     depends
    1.20
     muzzle
    1.16
     Gore
    1.14
    azeera
    1.09
     msec
    1.08
     multiplied
    1.08
    Activations Density 0.031%

    No Known Activations