INDEX

Explanations

intensifiers that emphasize the extent or degree of an attribute

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

Adverbs that intensify adjectives or adverbs

np_acts-logits-general · gemini-2.0-flash

intensifier followed by descriptor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Билгалдахарш

-0.59

$_['

-0.58

 estekak

-0.51

ดัง

-0.48

 الرياضيه

-0.47

Хьажоргаш

-0.46

 برانيه

-0.45

 Lese

-0.45

guiente

-0.45

 Steine

-0.45

POSITIVE LOGITS

 completely

1.00

 totally

0.96

 Completely

0.83

totally

0.81

completely

0.80

 entirely

0.80

Completely

0.79

 utterly

0.75

 Totally

0.74

Totally

0.71

Activations Density 0.202%

intensifiers that emphasize the extent or degree of an attribute

Adverbs that intensify adjectives or adverbs

intensifier followed by descriptor

No Comments

No Known Activations