© 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. 21785
    Prev
    Next
    INDEX
    Explanations

    terms related to physical injuries and their consequences

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.03
    4:0.05
    5:0.08
    6:0.02
    7:0.05
    8:0.01
    9:0.50
    10:0.02
    11:0.13
    Negative Logits
     advocate
    -2.39
     foc
    -2.23
     Educ
    -2.23
     Advocate
    -2.18
    inally
    -2.08
     Scholar
    -2.01
     esteemed
    -2.00
     basis
    -2.00
     focused
    -1.97
     Abstract
    -1.96
    POSITIVE LOGITS
     deterioration
    4.25
     degradation
    4.19
     loss
    4.10
     malf
    4.00
     disasters
    3.99
     failures
    3.99
    loss
    3.96
     injuries
    3.96
     glitches
    3.96
     malfunction
    3.96
    Activations Density 1.119%

    No Known Activations