INDEX

Explanations

terms related to drinking and alcohol consumption

oai_token-act-pair · gpt-4o-mini Triggered by @bot

consuming liquids

np_acts-logits-general · gemini-2.0-flash

drinking contexts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.76

]")]

-0.66

strated

-0.60

 Reverso

-0.55

 Bonne

-0.51

modelBuilder

-0.51

arXiv

-0.51

 ✭✭

-0.48

 informée

-0.47

AntiForgeryToken

-0.47

POSITIVE LOGITS

 beverages

0.86

 bottles

0.82

 beverage

0.82

 drinkers

0.78

 BOTT

0.72

 drinker

0.71

 drinks

0.71

 bottle

0.70

 cocktails

0.68

XtraEditors

0.68

Activations Density 0.077%

terms related to drinking and alcohol consumption

consuming liquids

drinking contexts

No Comments

No Known Activations