INDEX

Explanations

phrases indicating necessity or potential in a scientific context

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

Preceding "be" and indicating necessity or possibility

np_acts-logits-general · gemini-2.0-flash

modal verb + be

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

對

-0.54

 Know

-0.54

Know

-0.52

ют

-0.52

Had

-0.50

对

-0.49

 Have

-0.49

San

-0.48

ian

-0.48

rafat

-0.47

POSITIVE LOGITS

 tartalomajánló

0.87

WriteBarrier

0.83

makeConstraints

0.83

findpost

0.79

tagHelperRunner

0.77

')")

0.74

RetentionPolicy

0.74

ValueStyle

0.74

verifyException

0.72

 itſelf

0.71

Activations Density 0.403%

phrases indicating necessity or potential in a scientific context

Preceding "be" and indicating necessity or possibility

modal verb + be

No Comments

No Known Activations