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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12978
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles or reports

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

    phrases about prominent individuals or entities involved in current events

    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
    0:0.01
    1:0.11
    2:0.09
    3:0.02
    4:0.01
    5:0.05
    6:0.06
    7:0.05
    8:0.31
    9:0.06
    10:0.08
    11:0.08
    Negative Logits
    istries
    -1.54
    iferation
    -1.45
     reputation
    -1.42
     corpus
    -1.39
     discharge
    -1.31
    �
    -1.31
    Downloadha
    -1.30
    ignty
    -1.29
    "],"
    -1.28
    soever
    -1.28
    POSITIVE LOGITS
    cat
    1.37
     hatched
    1.36
    liest
    1.29
     swall
    1.27
    Cat
    1.27
     underestimated
    1.24
     Butcher
    1.23
     Tale
    1.23
     timed
    1.23
     hadn
    1.21
    Activations Density 0.078%

    No Known Activations