INDEX

Explanations

instances of the word "that."

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

"That" followed by a pronoun or article

np_acts-logits-general · gemini-2.0-flash

that plus clause

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.80

+#+#

-0.69

 Commencez

-0.68

Bronnen

-0.62

__((

-0.56

RDP

-0.56

 ourselves

-0.55

ตร์

-0.53

 jenner

-0.53

paravant

-0.52

POSITIVE LOGITS

 there

0.98

 they

0.94

there

0.76

 THERE

0.66

 THAT

0.62

 endwhile

0.60

he

0.59

 that

0.58

bootstrapcdn

0.57

that

0.57

Activations Density 0.278%

instances of the word "that."

"That" followed by a pronoun or article

that plus clause

No Comments

No Known Activations