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. 7229
    Prev
    Next
    INDEX
    Explanations

    terms related to high financial costs or significant rates

    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
    1:0.02
    2:0.10
    3:0.06
    4:0.06
    5:0.02
    6:0.04
    7:0.34
    8:0.04
    9:0.04
    10:0.08
    11:0.13
    Negative Logits
    ッド
    -1.47
    idem
    -1.36
    owler
    -1.33
    grave
    -1.32
     Stra
    -1.29
    sole
    -1.26
    avid
    -1.24
    zsche
    -1.24
     goodbye
    -1.23
    20439
    -1.23
    POSITIVE LOGITS
     quotas
    1.35
     levels
    1.28
     heights
    1.26
    Bytes
    1.22
     overhead
    1.22
     Converted
    1.21
     attendance
    1.21
    Demand
    1.20
     ceilings
    1.20
    fficient
    1.19
    Activations Density 0.000%

    No Known Activations