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. 6316
    Prev
    Next
    INDEX
    Explanations

    titles related to the Star Wars franchise

    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
    0:0.18
    1:0.10
    2:0.03
    3:0.01
    4:0.05
    5:0.21
    6:0.03
    7:0.06
    8:0.02
    9:0.02
    10:0.03
    11:0.20
    Negative Logits
    etheless
    -1.29
     amounts
    -1.25
     peripher
    -1.22
    mone
    -1.21
     possible
    -1.21
     financially
    -1.17
     along
    -1.17
     defensively
    -1.16
     totals
    -1.14
     capable
    -1.14
    POSITIVE LOGITS
     Excellence
    1.61
    ��
    1.53
     Lumpur
    1.45
     Honour
    1.43
     Society
    1.40
     Majesty
    1.37
     Adventures
    1.36
     Sisters
    1.33
     Companion
    1.32
     Incarn
    1.31
    Activations Density 0.316%

    No Known Activations