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. 1-ATT-KK
    6. 6452
    Prev
    Next
    INDEX
    Explanations

    measurements and descriptions related to sizes and dimensions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.49
    1:0.07
    2:0.03
    3:0.02
    4:0.04
    5:0.05
    6:0.03
    7:0.04
    8:0.02
    9:0.03
    10:0.02
    11:0.11
    Negative Logits
    ufact
    -1.84
     comr
    -1.63
    ciating
    -1.58
     Afric
    -1.57
     Lua
    -1.53
     tremend
    -1.45
     Cannot
    -1.42
     citiz
    -1.42
    ale
    -1.41
    ortunately
    -1.39
    POSITIVE LOGITS
    utan
    1.80
     IMAGES
    1.79
     reins
    1.69
    eper
    1.65
    teenth
    1.61
    irez
    1.54
    iffin
    1.52
     Mbps
    1.50
     buckets
    1.49
    7601
    1.45
    Activations Density 0.095%

    No Known Activations