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. 7-ATT-KK
    6. 9145
    Prev
    Next
    INDEX
    Explanations

    references to user merit and activity in online platforms

    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
    0:0.09
    1:0.09
    2:0.05
    3:0.13
    4:0.05
    5:0.05
    6:0.10
    7:0.07
    8:0.10
    9:0.12
    10:0.05
    11:0.04
    Negative Logits
     numbering
    -2.08
    icum
    -1.87
    racuse
    -1.77
    ��
    -1.76
     Berm
    -1.76
     Hispan
    -1.75
    �
    -1.74
     helicop
    -1.72
     differe
    -1.71
     streng
    -1.69
    POSITIVE LOGITS
    iasco
    1.87
     Minecraft
    1.83
    weet
    1.79
     Zuckerberg
    1.75
     Bitcoin
    1.69
    ulz
    1.69
     Failed
    1.68
    Merit
    1.66
     IPO
    1.65
    noxious
    1.63
    Activations Density 0.001%

    No Known Activations