© 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. 10-ATT-KK
    11. 9284
    Prev
    Next
    INDEX
    Explanations

    concepts related to challenges and opportunities, particularly in social and personal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.01
    2:0.06
    3:0.04
    4:0.03
    5:0.25
    6:0.01
    7:0.03
    8:0.02
    9:0.40
    10:0.02
    11:0.05
    Negative Logits
     wiser
    -2.56
    Downloadha
    -2.21
    iries
    -2.18
    ibly
    -2.10
     moderates
    -2.08
    Sources
    -2.07
    doms
    -2.06
    ivably
    -2.06
     thugs
    -2.06
    ollah
    -2.05
    POSITIVE LOGITS
    otide
    2.56
     endeavour
    2.54
    rium
    2.31
     exercise
    2.29
     indeed
    2.28
    ointment
    2.25
    undrum
    2.25
    isation
    2.24
     understatement
    2.23
     combination
    2.21
    Activations Density 0.517%

    No Known Activations