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. 3-ATT-KK
    6. 10091
    Prev
    Next
    INDEX
    Explanations

    contextually significant adverbs and descriptors related to performance and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.15
    3:0.05
    4:0.01
    5:0.02
    6:0.05
    7:0.15
    8:0.21
    9:0.13
    10:0.07
    11:0.07
    Negative Logits
    NECT
    -1.21
     Phillips
    -1.03
    redo
    -1.01
     Byrne
    -0.97
    Wallet
    -0.94
     "$
    -0.93
     ingenuity
    -0.93
    Cu
    -0.92
    Options
    -0.92
     negotiators
    -0.91
    POSITIVE LOGITS
    hes
    1.27
    riter
    1.17
    uddenly
    1.16
    isen
    1.14
    arte
    1.10
    otten
    1.10
    itialized
    1.04
    adem
    1.04
    aturally
    1.04
    ibly
    1.01
    Activations Density 0.034%

    No Known Activations