© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12140
    Prev
    Next
    INDEX
    Explanations

    comparisons and evaluations using numbers or rankings

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

    phrases related to economic conditions and discussions

    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
    1:0.08
    2:0.09
    3:0.03
    4:0.02
    5:0.04
    6:0.07
    7:0.05
    8:0.04
    9:0.07
    10:0.07
    11:0.36
    Negative Logits
    rontal
    -1.47
    uci
    -1.32
     disbanded
    -1.29
    ttes
    -1.29
    gur
    -1.26
    inently
    -1.23
     resumed
    -1.23
    quished
    -1.22
    ahime
    -1.21
    aith
    -1.20
    POSITIVE LOGITS
    SourceFile
    1.40
    ?",
    1.37
    soever
    1.32
     versus
    1.30
    ◼
    1.22
     depends
    1.22
    /$
    1.22
    TEXTURE
    1.22
     seasoning
    1.21
    Solution
    1.20
    Activations Density 0.233%

    No Known Activations