INDEX

Explanations

intensifiers that modify adjectives or adverbs, particularly the word "quite."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 alla

-0.53

//}

-0.53

itiés

-0.53

[]>

-0.51

tal

-0.49

 estekak

-0.48

 تق

-0.47

 career

-0.47

 properties

-0.46

мера

-0.46

POSITIVE LOGITS

 виправивши

0.93

 doInBackground

0.87

setDo

0.84

出版年

0.84

providedIn

0.83

ISO

0.82

WriteTagHelper

0.80

sizeCache

0.80

__':

0.80

Datuak

0.78

Activations Density 0.064%

intensifiers that modify adjectives or adverbs, particularly the word "quite."

No Comments

No Known Activations