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. 9-ATT-KK
    6. 15
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.44
    2:0.03
    3:0.13
    4:0.03
    5:0.05
    6:0.03
    7:0.03
    8:0.05
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     various
    -2.52
    rawdownloadcloneembedreportprint
    -2.51
     particular
    -2.31
     specific
    -2.26
     Due
    -2.24
     viability
    -2.23
     success
    -2.07
     Committees
    -2.07
    Lastly
    -2.07
    ع
    -2.06
    POSITIVE LOGITS
    half
    3.11
    mares
    3.07
    trak
    2.71
     halves
    2.58
    mare
    2.51
    nas
    2.29
    racuse
    2.29
    Rat
    2.28
     Ratings
    2.28
    nine
    2.28
    Activations Density 0.003%

    No Known Activations