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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44300
    Prev
    Next
    INDEX
    Explanations

    numerical values representing large quantities or measurements, particularly in the context of years

    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
    0:0.09
    1:0.07
    2:0.06
    3:0.06
    4:0.08
    5:0.20
    6:0.08
    7:0.06
    8:0.05
    9:0.08
    10:0.06
    11:0.06
    Negative Logits
     selector
    -1.72
    uart
    -1.59
    Ctrl
    -1.53
    selection
    -1.52
    tags
    -1.49
    =""
    -1.47
    utsche
    -1.46
     allocation
    -1.46
    verages
    -1.45
     rollout
    -1.45
    POSITIVE LOGITS
    years
    1.79
     yr
    1.59
     Ago
    1.57
    inia
    1.56
     Hume
    1.49
     Magicka
    1.49
    etimes
    1.48
    erc
    1.48
    omed
    1.47
     antiquity
    1.46
    Activations Density 0.000%

    No Known Activations