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. 27449
    Prev
    Next
    INDEX
    Explanations

    instances of the word "long" used 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
    0:0.02
    1:0.03
    2:0.07
    3:0.07
    4:0.08
    5:0.05
    6:0.20
    7:0.04
    8:0.04
    9:0.05
    10:0.09
    11:0.22
    Negative Logits
    PDF
    -1.75
     pad
    -1.66
     pavement
    -1.65
     stub
    -1.51
     statute
    -1.47
     pave
    -1.46
    PRO
    -1.44
     filings
    -1.44
     dime
    -1.44
     PAGE
    -1.43
    POSITIVE LOGITS
    assador
    2.21
    EStream
    2.02
    hower
    1.66
    washer
    1.64
    netflix
    1.62
    hyde
    1.60
     Gifts
    1.59
    awaru
    1.58
    gars
    1.57
    agos
    1.55
    Activations Density 0.009%

    No Known Activations