INDEX

Explanations

clarity and precision in communication

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

"clear" or "clarify."

np_acts-logits-general · gemini-2.0-flash

clarity and explanation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

#+#

-0.80

 propTypes

-0.77

expandindo

-0.60

葵

-0.57

photobucket

-0.56

propTypes

-0.56

ншни

-0.55

antd

-0.55

IBarButtonItem

-0.54

usepackage

-0.53

POSITIVE LOGITS

 clarity

1.06

 unclear

1.03

 Clarity

1.00

Clarity

0.99

 clear

0.96

 CLEAR

0.93

 clearer

0.93

 Clear

0.92

Clear

0.91

 confusing

0.91

Activations Density 0.236%

clarity and precision in communication

"clear" or "clarify."

clarity and explanation

No Comments

No Known Activations