© 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. 5-ATT-KK
    11. 3432
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.10
    1:0.01
    2:0.15
    3:0.07
    4:0.06
    5:0.04
    6:0.07
    7:0.02
    8:0.09
    9:0.07
    10:0.13
    11:0.14
    Negative Logits
    APTER
    -1.27
    itely
    -1.26
    UTE
    -1.21
    ername
    -1.16
    eworks
    -1.15
    lished
    -1.09
    eared
    -1.09
    uted
    -1.05
    ovie
    -1.04
     "{
    -1.03
    POSITIVE LOGITS
     etc
    1.41
    Interstitial
    1.28
     impairment
    1.17
     syndrome
    1.17
    etc
    1.16
     cardiovascular
    1.15
    opathy
    1.11
    secondary
    1.10
     flu
    1.10
    ��
    1.10
    Activations Density 0.101%

    No Known Activations