Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27520
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurement and evaluation in various contexts

    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
    0:0.01
    1:0.01
    2:0.17
    3:0.10
    4:0.23
    5:0.03
    6:0.04
    7:0.14
    8:0.04
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    Congratulations
    -1.69
    eah
    -1.67
     Congratulations
    -1.64
    rats
    -1.59
     Flavoring
    -1.54
    yssey
    -1.52
    fell
    -1.51
    prus
    -1.50
    Joined
    -1.49
    �
    -1.48
    POSITIVE LOGITS
     cruc
    1.44
     manageable
    1.39
     alloy
    1.39
     stroke
    1.36
     heel
    1.35
     サーティワン
    1.34
     practicable
    1.33
     appropriate
    1.33
     prescribed
    1.32
    ":["
    1.32
    Activations Density 0.029%

    No Known Activations