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. 7-ATT-KK
    6. 18813
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and statistical data

    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
    0:0.31
    1:0.05
    2:0.00
    3:0.06
    4:0.06
    5:0.05
    6:0.05
    7:0.02
    8:0.26
    9:0.06
    10:0.02
    11:0.01
    Negative Logits
     Cake
    -1.71
    cakes
    -1.54
     Natasha
    -1.52
    cake
    -1.51
    rium
    -1.51
     Bringing
    -1.48
     Congratulations
    -1.46
     Builder
    -1.45
     Videos
    -1.41
     Flowers
    -1.40
    POSITIVE LOGITS
    itudes
    2.23
     intervals
    2.14
     disadvantage
    2.13
     speeds
    2.11
     frequency
    2.11
     discretion
    2.09
     velocity
    1.98
     detriment
    1.95
     extremes
    1.92
     angle
    1.92
    Activations Density 0.040%

    No Known Activations