INDEX

Explanations

first-person pronouns and related expressions in the text

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

"I" followed by a verb

np_acts-logits-general · gemini-2.0-flash

"I" followed by verbs

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

 even

-0.85

even

-0.80

 incluso

-0.71

 zelfs

-0.71

 sogar

-0.67

 даже

-0.65

 Even

-0.64

rxjs

-0.63

還會

-0.63

'])->

-0.62

POSITIVE LOGITS

 recently

0.68

 stumbled

0.60

Recently

0.58

 Roskov

0.58

 autorytatywna

0.57

recently

0.57

 недавно

0.56

Newly

0.55

 recientemente

0.55

LOV

0.53

Activations Density 0.221%

first-person pronouns and related expressions in the text

"I" followed by a verb

"I" followed by verbs

No Comments

No Known Activations