INDEX

Explanations

terms that indicate benefits or advantages in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ers

-0.71

-0.68

й

-0.67

-0.62

it

-0.62

izumi

-0.61

-0.60

the

-0.59

zmir

-0.58

olol

-0.57

POSITIVE LOGITS

 Vantage

1.27

 estimés

1.25

 تضيفلها

1.13

 itſelf

1.12

 Disadvantages

1.08

 ligiloj

1.05

 disadvantages

1.03

 Advantage

1.03

 disadvantage

1.01

 propOrder

1.00

Activations Density 0.073%

terms that indicate benefits or advantages in various contexts

No Comments

No Known Activations