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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7828
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.06
    3:0.31
    4:0.04
    5:0.03
    6:0.07
    7:0.14
    8:0.05
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
     Unloaded
    -1.42
     resil
    -1.41
    DragonMagazine
    -1.40
    fw
    -1.37
    catentry
    -1.26
    terson
    -1.25
    isSpecialOrderable
    -1.24
    ellar
    -1.21
    solete
    -1.16
    GGGGGGGG
    -1.16
    POSITIVE LOGITS
    ijk
    1.56
    tein
    1.28
     Moreno
    1.22
     asc
    1.18
    ppings
    1.12
    uay
    1.11
     Mansion
    1.11
     Ree
    1.11
     Cu
    1.09
     Lama
    1.06
    Activations Density 0.005%

    No Known Activations