© 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. 43499
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal drugs and their effects, particularly focusing on cocaine and heroin

    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
    2:0.05
    3:0.03
    4:0.04
    5:0.05
    6:0.04
    7:0.04
    8:0.04
    9:0.08
    10:0.43
    11:0.09
    Negative Logits
     delegate
    -1.90
    natureconservancy
    -1.82
     vot
    -1.76
     Utt
    -1.74
     radiant
    -1.69
     Eag
    -1.68
     delegates
    -1.68
     NOAA
    -1.64
     canv
    -1.61
     Tribal
    -1.59
    POSITIVE LOGITS
    hetamine
    2.52
     addictive
    2.21
     drugs
    2.20
    drug
    2.12
    killers
    2.03
     cocaine
    2.02
    amphetamine
    2.00
    igma
    1.97
    killer
    1.97
     drug
    1.96
    Activations Density 0.080%

    No Known Activations