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. 7175
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific locations and measurements in a variety of 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
    1:0.01
    2:0.12
    3:0.09
    4:0.11
    5:0.03
    6:0.04
    7:0.29
    8:0.03
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     parted
    -1.95
     taboo
    -1.79
    aft
    -1.75
    odan
    -1.66
    aido
    -1.65
    minded
    -1.65
     dared
    -1.65
    ecided
    -1.60
     passionately
    -1.59
     vowed
    -1.58
    POSITIVE LOGITS
     Exhibit
    1.89
     Grimoire
    1.66
     Login
    1.54
     Supplemental
    1.50
     Portable
    1.50
     signatures
    1.48
     Frames
    1.47
    kson
    1.45
     metadata
    1.44
     Incre
    1.44
    Activations Density 0.002%

    No Known Activations