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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7565
    Prev
    Next
    INDEX
    Explanations

    references to political party affiliations and sentiments

    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
    0:0.12
    1:0.01
    2:0.15
    3:0.06
    4:0.08
    5:0.03
    6:0.07
    7:0.02
    8:0.14
    9:0.03
    10:0.07
    11:0.16
    Negative Logits
    ftime
    -1.63
    vote
    -1.42
     rehe
    -1.39
     aisle
    -1.37
     plurality
    -1.35
     throb
    -1.34
    orum
    -1.34
     bip
    -1.29
     clot
    -1.27
     Votes
    -1.26
    POSITIVE LOGITS
     alike
    1.84
    iliated
    1.63
     Gamma
    1.49
    ossal
    1.42
     typh
    1.37
    undy
    1.33
     respectively
    1.32
     Typh
    1.30
    GV
    1.30
    esters
    1.27
    Activations Density 0.018%

    No Known Activations