Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19254
    Prev
    Next
    INDEX
    Explanations

    references to sports, particularly boxing and other physical activities

    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
    2:0.07
    3:0.05
    4:0.07
    5:0.04
    6:0.09
    7:0.36
    8:0.03
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
     defic
    -1.59
     replacements
    -1.55
    answered
    -1.51
     effic
    -1.50
     devote
    -1.47
     urgent
    -1.47
     ingred
    -1.46
     reinforcements
    -1.46
     preparations
    -1.46
     helpful
    -1.45
    POSITIVE LOGITS
    ��
    1.67
    iage
    1.58
     Mayhem
    1.55
    football
    1.53
    omy
    1.51
     Championships
    1.50
     Robotics
    1.49
    horse
    1.49
     Guinness
    1.47
     Carnival
    1.47
    Activations Density 0.000%

    No Known Activations