© 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. 10-ATT-KK
    11. 21000
    Prev
    Next
    INDEX
    Explanations

    concepts related to clarity and resolution in various 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
    0:0.04
    1:0.04
    2:0.03
    3:0.04
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.02
    9:0.10
    10:0.04
    11:0.45
    Negative Logits
    CTV
    -2.07
     joke
    -2.06
    warming
    -2.02
    relations
    -1.98
     anecdote
    -1.97
     Idea
    -1.96
    reprene
    -1.95
    exclusive
    -1.94
    cos
    -1.94
    verted
    -1.91
    POSITIVE LOGITS
     hurdles
    3.19
     clutter
    2.99
     backlog
    2.93
     slate
    2.93
     hurdle
    2.84
     waivers
    2.77
     rubble
    2.65
     labels
    2.65
     fields
    2.64
     label
    2.58
    Activations Density 0.006%

    No Known Activations