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. 10-ATT-KK
    6. 14578
    Prev
    Next
    INDEX
    Explanations

    references to connections or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.07
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Hert
    -3.14
     Hermes
    -2.93
     Berm
    -2.84
     Henderson
    -2.83
     Norton
    -2.77
     Tornado
    -2.72
     Hend
    -2.68
     Rack
    -2.64
     Niger
    -2.64
     Bentley
    -2.60
    POSITIVE LOGITS
    �
    3.13
    utenberg
    2.93
    DragonMagazine
    2.84
     Flavoring
    2.80
    EStreamFrame
    2.72
    AFTA
    2.68
    ainment
    2.45
    liga
    2.45
     viz
    2.42
    APTER
    2.40
    Activations Density 0.000%

    No Known Activations