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. 3050
    Prev
    Next
    INDEX
    Explanations

    names of political parties and movements

    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
    0:0.06
    1:0.13
    2:0.03
    3:0.04
    4:0.04
    5:0.30
    6:0.03
    7:0.02
    8:0.03
    9:0.06
    10:0.13
    11:0.07
    Negative Logits
    nown
    -1.72
     aval
    -1.63
     extingu
    -1.59
     accommodation
    -1.58
     rearr
    -1.58
     dele
    -1.51
     invol
    -1.51
     CrossRef
    -1.50
     eas
    -1.47
     detain
    -1.43
    POSITIVE LOGITS
    Party
    2.32
     Party
    2.31
     Voters
    2.30
    Vote
    2.28
    Democrats
    2.23
    Republicans
    2.11
     Democrats
    2.07
     Conservatives
    2.05
     Dems
    2.01
    party
    2.00
    Activations Density 0.007%

    No Known Activations