© 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. 3-ATT-KK
    11. 12057
    Prev
    Next
    INDEX
    Explanations

    terms related to bacteria species, specifically Staphylococcus aureus

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of bacteria or pathogens linked to health-related studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.06
    2:0.09
    3:0.12
    4:0.03
    5:0.05
    6:0.11
    7:0.14
    8:0.06
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    staking
    -1.29
    cipled
    -1.29
    ftime
    -1.20
     podium
    -1.15
    FORM
    -1.15
    soDeliveryDate
    -1.13
    reement
    -1.11
    tty
    -1.08
     deadline
    -1.08
     slot
    -1.08
    POSITIVE LOGITS
    aceae
    1.32
    esson
    1.27
     Trace
    1.23
    idae
    1.22
     overe
    1.22
     Virus
    1.19
     bacteria
    1.18
     coli
    1.16
     detected
    1.15
     bacterial
    1.10
    Activations Density 0.004%

    No Known Activations