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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23204
    Prev
    Next
    INDEX
    Explanations

    information related to news events and locations, such as accidents, political events, and public activities

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

    dates and numerical values associated with events

    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
    0:0.05
    1:0.04
    2:0.07
    3:0.11
    4:0.10
    5:0.10
    6:0.07
    7:0.04
    8:0.08
    9:0.15
    10:0.09
    11:0.04
    Negative Logits
     analogy
    -1.38
     lately
    -1.27
     dict
    -1.18
    onom
    -1.09
     nowadays
    -1.07
    dict
    -1.04
    Cub
    -1.03
     domest
    -1.02
    onomy
    -1.01
     dictators
    -1.01
    POSITIVE LOGITS
    icken
    1.35
    Interstitial
    1.30
    ILLE
    1.25
    stice
    1.25
    ember
    1.25
     Parade
    1.19
    heny
    1.18
     hrs
    1.15
    aucus
    1.15
    aundering
    1.11
    Activations Density 0.056%

    No Known Activations