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. 10-ATT-KK
    6. 14687
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.09
    5:0.09
    6:0.07
    7:0.08
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     Polly
    -3.11
     Peck
    -2.99
     Corker
    -2.96
     Pike
    -2.82
     Lydia
    -2.76
     Waters
    -2.74
     Patt
    -2.71
     Joyce
    -2.67
    OPA
    -2.62
     Petersen
    -2.62
    POSITIVE LOGITS
    doms
    2.86
    fu
    2.73
     hides
    2.65
     wastes
    2.54
     welf
    2.50
    FactoryReloaded
    2.46
    cht
    2.46
     Omn
    2.45
     deceive
    2.43
     accur
    2.42
    Activations Density 0.000%

    No Known Activations