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. 44238
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical agreements and international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.00
    2:0.07
    3:0.05
    4:0.17
    5:0.02
    6:0.11
    7:0.31
    8:0.02
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    iewicz
    -1.72
    nikov
    -1.61
    rpm
    -1.57
    ruciating
    -1.50
    unknown
    -1.50
    renheit
    -1.47
    ommel
    -1.47
    acher
    -1.43
    uzz
    -1.38
    zeb
    -1.34
    POSITIVE LOGITS
     curfew
    1.53
     contrace
    1.51
     parade
    1.47
     voluntarily
    1.44
     portfolio
    1.43
     prematurely
    1.42
     waivers
    1.41
     hypers
    1.41
     permit
    1.39
     gamble
    1.34
    Activations Density 0.002%

    No Known Activations