INDEX

Explanations

phrases indicating positive evaluations or quality assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Schaefer

-0.88

 onItemClick

-0.81

 whoſe

-0.80

 Nugent

-0.80

bootstrapcdn

-0.75

ᾶ

-0.74

ობ

-0.74

 DiCaprio

-0.74

 оригіналу

-0.73

jstor

-0.72

POSITIVE LOGITS

 well

1.37

 WELL

1.37

 Well

1.32

well

1.27

Well

1.26

 Wells

1.25

 wells

1.20

Wells

1.19

 Welles

1.15

 WELLS

1.09

Activations Density 0.104%

phrases indicating positive evaluations or quality assessments

No Comments

No Known Activations