© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22897
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental actions

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

    references to government actions and policies

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.07
    4:0.03
    5:0.09
    6:0.04
    7:0.04
    8:0.03
    9:0.37
    10:0.07
    11:0.04
    Negative Logits
     occurrence
    -1.30
    etimes
    -1.29
     vortex
    -1.27
     teammate
    -1.19
    Interstitial
    -1.18
    rament
    -1.18
     ancest
    -1.15
     poems
    -1.13
     teammates
    -1.12
     karma
    -1.12
    POSITIVE LOGITS
     appoint
    1.54
    orses
    1.42
    �
    1.41
    istries
    1.39
     Brady
    1.34
    �醒
    1.27
     Regulations
    1.27
     legisl
    1.27
    funding
    1.26
    verning
    1.25
    Activations Density 0.157%

    No Known Activations