© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 42797
    Prev
    Next
    INDEX
    Explanations

    chemical compounds related to drugs or medications

    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
    1:0.02
    2:0.16
    3:0.08
    4:0.06
    5:0.04
    6:0.09
    7:0.05
    8:0.07
    9:0.08
    10:0.16
    11:0.10
    Negative Logits
     moderation
    -1.26
     weaknesses
    -1.26
     mileage
    -1.26
    ownt
    -1.23
     fairness
    -1.23
     sabotage
    -1.21
     mitigating
    -1.21
     insecurity
    -1.20
     faults
    -1.19
     discipline
    -1.17
    POSITIVE LOGITS
     respectively
    1.70
    versible
    1.55
    ^{
    1.52
    ���
    1.47
     Analog
    1.36
    azo
    1.30
    termin
    1.30
    osal
    1.28
    sided
    1.27
    )-
    1.21
    Activations Density 0.003%

    No Known Activations