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. 7090
    Prev
    Next
    INDEX
    Explanations

    phrases or prepositions related to time

    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
    2:0.13
    3:0.09
    4:0.20
    5:0.04
    6:0.05
    7:0.21
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    atures
    -1.55
    lihood
    -1.44
    quartered
    -1.43
    iquette
    -1.39
    ologue
    -1.35
    utable
    -1.33
    igne
    -1.33
     fit
    -1.33
    iver
    -1.31
    ossier
    -1.29
    POSITIVE LOGITS
     recons
    1.43
     prest
    1.36
    fm
    1.35
     awhile
    1.34
     sanity
    1.32
     refres
    1.31
     depleted
    1.30
    zb
    1.29
    fal
    1.29
     showc
    1.26
    Activations Density 0.011%

    No Known Activations