© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 8512
    Prev
    Next
    INDEX
    Explanations

    references to improvements, changes, or positive developments 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
    0:0.05
    1:0.16
    2:0.06
    3:0.08
    4:0.20
    5:0.03
    6:0.06
    7:0.13
    8:0.02
    9:0.05
    10:0.04
    11:0.07
    Negative Logits
     oppos
    -2.69
    uyomi
    -2.63
    channelAvailability
    -2.48
    veyard
    -2.35
    soType
    -2.30
     unthinkable
    -2.18
    UME
    -2.13
    oros
    -2.08
     mosqu
    -2.08
    alg
    -2.04
    POSITIVE LOGITS
     improvements
    6.10
     improved
    6.07
     improvement
    5.86
    Improve
    5.64
    improve
    5.61
     improve
    5.50
    Improved
    5.40
     improves
    5.23
     Improved
    5.17
     improving
    5.16
    Activations Density 0.068%

    No Known Activations