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. 9-ATT-KK
    6. 20624
    Prev
    Next
    INDEX
    Explanations

    references to the Quran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.07
    3:0.07
    4:0.09
    5:0.09
    6:0.06
    7:0.09
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    igers
    -2.79
    kees
    -2.71
    psons
    -2.65
    ags
    -2.53
    culosis
    -2.45
    tc
    -2.45
    oyd
    -2.44
    payer
    -2.44
     Pastebin
    -2.44
    ername
    -2.39
    POSITIVE LOGITS
     Alps
    2.49
     daemon
    2.38
     autumn
    2.37
     IA
    2.36
     glac
    2.34
     1917
    2.32
     generational
    2.31
     condensed
    2.30
     primaries
    2.24
     Caucasus
    2.20
    Activations Density 0.000%

    No Known Activations