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. 10-ATT-KK
    6. 14738
    Prev
    Next
    INDEX
    Explanations

    the importance of suggested practices or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.19
    2:0.06
    3:0.05
    4:0.05
    5:0.03
    6:0.09
    7:0.07
    8:0.04
    9:0.04
    10:0.13
    11:0.07
    Negative Logits
     fil
    -2.87
     Serv
    -2.79
    served
    -2.79
     gifts
    -2.68
    oven
    -2.65
     personalized
    -2.62
    addin
    -2.50
     gift
    -2.49
    suit
    -2.47
    RNA
    -2.47
    POSITIVE LOGITS
     Cliff
    7.33
     cliff
    4.55
     cliffs
    4.05
     CL
    3.72
     Cob
    3.54
     Crash
    3.49
     Reneg
    3.48
     Clim
    3.41
     Jeremiah
    3.25
     Coffin
    3.25
    Activations Density 0.000%

    No Known Activations