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. 10085
    Prev
    Next
    INDEX
    Explanations

    instances of specific symbols or characters that might indicate parts of a document layout or navigation

    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
    0:0.01
    1:0.14
    2:0.06
    3:0.20
    4:0.02
    5:0.04
    6:0.06
    7:0.09
    8:0.05
    9:0.18
    10:0.05
    11:0.05
    Negative Logits
    icken
    -1.35
    onne
    -1.34
     abstinence
    -1.32
    sample
    -1.18
    arcity
    -1.17
     intrins
    -1.15
     recip
    -1.14
    urers
    -1.13
     Punk
    -1.13
     electors
    -1.13
    POSITIVE LOGITS
     IMAGES
    1.71
    yright
    1.34
    Enlarge
    1.32
    Pull
    1.25
    ヴァ
    1.23
    iership
    1.22
     Shutterstock
    1.19
    isl
    1.19
    VPN
    1.18
    ||||
    1.18
    Activations Density 0.002%

    No Known Activations