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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7543
    Prev
    Next
    INDEX
    Explanations

    instances of the word "because."

    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
    2:0.08
    3:0.11
    4:0.15
    5:0.04
    6:0.05
    7:0.18
    8:0.03
    9:0.04
    10:0.07
    11:0.15
    Negative Logits
    scription
    -1.68
    scribe
    -1.56
    daq
    -1.55
    ipel
    -1.50
    icter
    -1.49
    urnal
    -1.45
    yles
    -1.44
    eli
    -1.44
    ocket
    -1.40
     lashes
    -1.39
    POSITIVE LOGITS
     Overs
    1.61
     Ü
    1.53
    atown
    1.43
     ≡
    1.42
     Friedrich
    1.40
     exha
    1.40
     cumbers
    1.40
     Wolfgang
    1.39
     Spiegel
    1.39
     Jung
    1.37
    Activations Density 0.003%

    No Known Activations