INDEX

Explanations

articles and demonstrative adjectives emphasizing the indefinite article "an."

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

"an" before positive adjectives

np_acts-logits-general · gemini-2.0-flash

an followed by a descriptor

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orologio

-0.73

égard

-0.72

écoute

-0.71

assemblée

-0.69

apprendre

-0.68

WriteTagHelper

-0.68

 MenuView

-0.68

empereur

-0.66

altezza

-0.64

hébergement

-0.64

POSITIVE LOGITS

 array

0.73

 extra

0.73

 active

0.71

 excellent

0.71

 amazing

0.71

 additional

0.71

 important

0.70

 opportunity

0.70

 appropriate

0.70

 average

0.68

Activations Density 0.233%

articles and demonstrative adjectives emphasizing the indefinite article "an."

"an" before positive adjectives

an followed by a descriptor

No Comments

No Known Activations