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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44271
    Prev
    Next
    INDEX
    Explanations

    references to famous movie titles and their related details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.08
    1:0.02
    2:0.11
    3:0.10
    4:0.06
    5:0.06
    6:0.02
    7:0.03
    8:0.09
    9:0.10
    10:0.14
    11:0.14
    Negative Logits
    >>\
    -1.53
    norm
    -1.27
    ée
    -1.27
    agents
    -1.21
    .............
    -1.18
    minist
    -1.16
    >:
    -1.15
    aye
    -1.13
    nels
    -1.10
    aster
    -1.08
    POSITIVE LOGITS
     Booker
    1.40
     cameo
    1.22
     Chess
    1.19
     favorites
    1.16
     Spoiler
    1.14
     Spielberg
    1.13
     Compton
    1.13
     MSG
    1.12
     Warner
    1.12
     autobi
    1.12
    Activations Density 0.220%

    No Known Activations