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. 5-ATT-KK
    6. 3018
    Prev
    Next
    INDEX
    Explanations

    comments and explanations related to programming concepts and best practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.07
    3:0.13
    4:0.06
    5:0.06
    6:0.02
    7:0.05
    8:0.07
    9:0.11
    10:0.21
    11:0.12
    Negative Logits
    ée
    -1.20
    hua
    -1.10
    upe
    -1.04
     inscribed
    -1.03
    worn
    -1.02
    iannopoulos
    -1.02
     roared
    -0.99
    aucas
    -0.98
    reetings
    -0.98
     propelled
    -0.97
    POSITIVE LOGITS
     homebrew
    1.37
     GPL
    1.37
     debugging
    1.33
    RFC
    1.26
     hiber
    1.25
     prag
    1.25
     override
    1.24
     debugger
    1.21
     REPL
    1.19
     semantics
    1.19
    Activations Density 0.477%

    No Known Activations