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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10685
    Prev
    Next
    INDEX
    Explanations

    references to past events and interactions

    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
    1:0.02
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.28
    7:0.05
    8:0.07
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
     Chains
    -3.64
     Mog
    -3.62
    ~~~~~~~~
    -3.52
     dst
    -3.50
     EG
    -3.44
    jah
    -3.41
    ince
    -3.39
    illance
    -3.38
     sarc
    -3.35
     enz
    -3.34
    POSITIVE LOGITS
     Palmer
    12.02
    Pal
    8.82
     Pal
    6.56
    pal
    5.75
     PAL
    5.37
     Palm
    5.05
     Palin
    4.79
     pal
    4.46
     Paladin
    4.21
     Clive
    4.08
    Activations Density 0.004%

    No Known Activations