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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18705
    Prev
    Next
    INDEX
    Explanations

    references to political parties, particularly Republican candidates and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.10
    2:0.06
    3:0.07
    4:0.07
    5:0.05
    6:0.19
    7:0.05
    8:0.02
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
     Walls
    -3.57
     Wu
    -3.54
     Razer
    -3.43
     Hook
    -3.37
     Wheeler
    -3.34
     VID
    -3.29
     Fried
    -3.29
     Frie
    -3.19
    Wheel
    -3.13
     Wass
    -3.10
    POSITIVE LOGITS
     candidate
    5.44
     candidates
    5.35
    cand
    4.91
     Candidate
    4.85
     candidacy
    4.51
    Cand
    4.28
    idates
    4.01
     aspir
    3.85
     nominee
    3.42
     Cand
    3.38
    Activations Density 0.002%

    No Known Activations