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. 7751
    Prev
    Next
    INDEX
    Explanations

    terms related to operations and processes, particularly in a financial or organizational context

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.34
    4:0.02
    5:0.02
    6:0.11
    7:0.04
    8:0.03
    9:0.08
    10:0.08
    11:0.12
    Negative Logits
    ItemThumbnailImage
    -1.29
    Synopsis
    -1.12
    VK
    -1.10
     srfAttach
    -1.09
    cgi
    -1.06
     grill
    -1.05
     qualifications
    -1.05
    =-=-=-=-=-=-=-=-
    -1.03
     millisec
    -1.03
     importance
    -1.03
    POSITIVE LOGITS
    rency
    1.84
    cious
    1.36
    furt
    1.35
    ucle
    1.27
    hesive
    1.26
    rences
    1.26
    ulative
    1.24
    lished
    1.22
    nect
    1.22
    endant
    1.21
    Activations Density 0.024%

    No Known Activations