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. 6322
    Prev
    Next
    INDEX
    Explanations

    references to superheroes and supernatural abilities

    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
    0:0.09
    1:0.06
    2:0.03
    3:0.02
    4:0.05
    5:0.15
    6:0.20
    7:0.07
    8:0.04
    9:0.04
    10:0.03
    11:0.17
    Negative Logits
    76561
    -1.44
     Comments
    -1.35
     unfocusedRange
    -1.29
     Featured
    -1.27
    cade
    -1.25
     exhib
    -1.23
    BuyableInstoreAndOnline
    -1.21
    aturdays
    -1.20
    NW
    -1.20
    JM
    -1.19
    POSITIVE LOGITS
    agine
    1.38
     Scully
    1.34
    bard
    1.26
     Kenobi
    1.21
     dummy
    1.20
     Jinn
    1.20
     Uz
    1.18
    \'
    1.17
     Helena
    1.15
     Cooke
    1.15
    Activations Density 0.022%

    No Known Activations