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. 7587
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in quotations

    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
    0:0.12
    1:0.03
    2:0.07
    3:0.04
    4:0.05
    5:0.04
    6:0.15
    7:0.05
    8:0.09
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
    LAB
    -3.74
    alg
    -3.64
     certs
    -3.61
    gdala
    -3.60
    auga
    -3.54
     ABE
    -3.54
    ulhu
    -3.51
    apon
    -3.51
    agu
    -3.49
     Baird
    -3.44
    POSITIVE LOGITS
     Von
    9.96
     von
    7.79
    von
    6.38
     Vander
    6.38
    Van
    5.21
     Van
    4.67
     Schwarz
    4.50
     Zur
    4.39
     VK
    4.33
     van
    4.23
    Activations Density 0.002%

    No Known Activations