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. 2-ATT-KK
    6. 22446
    Prev
    Next
    INDEX
    Explanations

    words related to political opinions and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    support for various government policies and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.14
    3:0.09
    4:0.06
    5:0.10
    6:0.02
    7:0.02
    8:0.20
    9:0.13
    10:0.05
    11:0.02
    Negative Logits
    stress
    -1.33
    lance
    -1.24
     pandemonium
    -1.20
    oche
    -1.16
    版
    -1.15
    ��
    -1.15
     Sao
    -1.15
     Bride
    -1.14
    ulhu
    -1.12
    orld
    -1.11
    POSITIVE LOGITS
     paternal
    1.12
     pronouns
    1.10
    ilitarian
    1.08
     filibuster
    1.07
     Cosponsors
    1.06
    AFTA
    1.05
     neutrality
    1.05
    tein
    1.05
    avorable
    1.04
    essim
    1.04
    Activations Density 0.010%

    No Known Activations