INDEX

Explanations

phrases related to policy adjustments and healthcare implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Roskov

-0.78

scriptcase

-0.57

 prati

-0.55

Portale

-0.51

 Deter

-0.49

 integration

-0.49

 anjo

-0.48

 citer

-0.46

trace

-0.46

 judíos

-0.46

POSITIVE LOGITS

NOPQRST

0.65

 compensate

0.63

存于互联网档案馆

0.61

 compensatory

0.61

__);

0.59

 الحره

0.58

ỡng

0.58

(&:

0.57

แก้

0.56

 חיצוניים

0.56

Activations Density 0.338%

phrases related to policy adjustments and healthcare implications

No Comments

No Known Activations