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. 3-ATT-KK
    6. 8586
    Prev
    Next
    INDEX
    Explanations

    references to political processes and events, particularly regarding the Senate and voting dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.02
    2:0.08
    3:0.04
    4:0.03
    5:0.05
    6:0.17
    7:0.34
    8:0.05
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    uni
    -1.26
     iceberg
    -1.19
    jiang
    -1.19
     narration
    -1.14
    dylib
    -1.13
    エル
    -1.12
    idious
    -1.10
    1920
    -1.09
    Sov
    -1.09
    ャ
    -1.09
    POSITIVE LOGITS
     jurisdiction
    1.23
     Judiciary
    1.21
     recess
    1.21
     Holder
    1.16
     Caucus
    1.16
     Appropriations
    1.14
     Sonia
    1.12
     Majority
    1.09
     appoint
    1.09
    hess
    1.08
    Activations Density 0.020%

    No Known Activations