© 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. 3-ATT-KK
    11. 12894
    Prev
    Next
    INDEX
    Explanations

    words related to side effects and health concerns

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

    phrases related to side effects of medical treatments

    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
    0:0.01
    1:0.03
    2:0.07
    3:0.12
    4:0.03
    5:0.06
    6:0.07
    7:0.26
    8:0.06
    9:0.06
    10:0.05
    11:0.13
    Negative Logits
    soDeliveryDate
    -1.94
    OWS
    -1.40
    ░
    -1.39
    isle
    -1.30
    enture
    -1.26
    assies
    -1.22
    aunder
    -1.22
    ledged
    -1.20
    KN
    -1.19
    OV
    -1.17
    POSITIVE LOGITS
     awa
    1.60
    ���
    1.44
     digestion
    1.36
     medications
    1.35
     medication
    1.31
     slowing
    1.30
     exacerbated
    1.25
     occurring
    1.24
     illnesses
    1.24
     incurred
    1.23
    Activations Density 0.003%

    No Known Activations