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. 3021
    Prev
    Next
    INDEX
    Explanations

    trends and changes in numerical data or statistics

    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
    0:0.02
    1:0.01
    2:0.09
    3:0.05
    4:0.08
    5:0.03
    6:0.05
    7:0.03
    8:0.04
    9:0.03
    10:0.16
    11:0.36
    Negative Logits
     forecasting
    -1.56
     quake
    -1.50
     lows
    -1.48
     earthquakes
    -1.47
     recession
    -1.44
     buoy
    -1.40
    flation
    -1.40
    culation
    -1.39
     seismic
    -1.38
    ixels
    -1.38
    POSITIVE LOGITS
    ���
    1.87
    ______
    1.40
    ,,,,
    1.37
     Hoff
    1.33
    rolet
    1.32
    anooga
    1.29
     Liu
    1.28
     Hatt
    1.27
     Nam
    1.27
     Hann
    1.26
    Activations Density 0.257%

    No Known Activations