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. 6311
    Prev
    Next
    INDEX
    Explanations

    references to sums of money or discounts

    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
    0:0.12
    1:0.12
    2:0.12
    3:0.04
    4:0.10
    5:0.07
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.10
    11:0.13
    Negative Logits
    lua
    -1.17
    bes
    -1.12
    do
    -1.11
     Lua
    -1.11
    vid
    -1.10
     Scandinavian
    -1.09
    ovie
    -1.08
    Hide
    -1.08
    edy
    -1.06
     Lovecraft
    -1.06
    POSITIVE LOGITS
     acres
    1.61
    undred
    1.38
     apiece
    1.35
     gestation
    1.35
     pounds
    1.31
     respectively
    1.29
     consecut
    1.27
     disapp
    1.25
    pees
    1.22
     cones
    1.19
    Activations Density 0.463%

    No Known Activations