INDEX

Explanations

the word "be" in various forms and contexts

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

"Be" (often capitalized)

np_acts-logits-general · gemini-2.0-flash

words starting with Be

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

extAlignment

-0.77

########.

-0.73

wußt

-0.70

bcrypt

-0.65

seteq

-0.60

éric

-0.60

 Económica

-0.58

awtextra

-0.58

principalColumn

-0.58

mapStateToProps

-0.58

POSITIVE LOGITS

Be

0.63

Be

0.55

Bew

0.54

Bef

0.52

BE

0.50

Bew

0.49

 havi

0.48

sidemargin

0.48

cause

0.45

CAUSE

0.45

Activations Density 0.131%

the word "be" in various forms and contexts

"Be" (often capitalized)

words starting with Be

No Comments

No Known Activations