INDEX

Explanations

words that signify changes over time or cause and effect relationships

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

"Then" or similar time-related words

np_acts-logits-general · gemini-2.0-flash

then

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

 vooraf

-0.79

 pourtant

-0.72

recently

-0.71

 Италијани

-0.70

 lately

-0.70

تقاوى

-0.70

 estekak

-0.69

 recently

-0.68

 estimés

-0.68

 Italijanski

-0.68

POSITIVE LOGITS

 proceed

1.12

 proceeded

1.12

Then

0.93

 further

0.93

 Then

0.91

 Далее

0.90

 proceeds

0.90

 then

0.89

Далее

0.88

 THEN

0.88

Activations Density 0.620%

words that signify changes over time or cause and effect relationships

"Then" or similar time-related words

then

No Comments

No Known Activations