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. 5-ATT-KK
    6. 7201
    Prev
    Next
    INDEX
    Explanations

    quantities or numerical data related to statistics or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.10
    3:0.06
    4:0.06
    5:0.14
    6:0.08
    7:0.07
    8:0.14
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
    Ku
    -1.86
    Party
    -1.66
    ghazi
    -1.65
    Fu
    -1.58
    voice
    -1.55
    Uk
    -1.53
    DERR
    -1.48
     ja
    -1.46
    Vice
    -1.46
    ズ
    -1.39
    POSITIVE LOGITS
     partName
    1.95
    hematically
    1.69
    adata
    1.67
    clusions
    1.66
     Scroll
    1.65
     istg
    1.64
     PDF
    1.61
    antha
    1.60
    iterator
    1.59
     Table
    1.58
    Activations Density 0.000%

    No Known Activations