© 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. 5-ATT-KK
    11. 45419
    Prev
    Next
    INDEX
    Explanations

    medical and biological terminology related to diseases, especially those affecting tissues, tumors, and inflammatory responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.17
    3:0.07
    4:0.04
    5:0.07
    6:0.11
    7:0.06
    8:0.04
    9:0.06
    10:0.15
    11:0.13
    Negative Logits
    selage
    -1.54
    omsky
    -1.42
    HUD
    -1.36
    ALSE
    -1.35
     sanity
    -1.34
     wiser
    -1.28
    Honest
    -1.28
    edIn
    -1.21
    OHN
    -1.20
    Fed
    -1.19
    POSITIVE LOGITS
    �醒
    1.20
     Chaser
    1.17
     distributed
    1.15
     Mé
    1.10
     Procedure
    1.10
    gal
    1.10
     ("
    1.08
     Gael
    1.08
     Photograph
    1.07
    culosis
    1.07
    Activations Density 0.082%

    No Known Activations