INDEX

Explanations

references to the pronoun "it."

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

"it" followed by specific prepositions or verbs

np_acts-logits-general · gemini-2.0-flash

it followed by preposition

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 strani

-0.54

ecken

-0.49

ambiental

-0.49

walkers

-0.48

 georg

-0.48

er

-0.47

bor

-0.47

 والأ

-0.46

 Carole

-0.46

ely

-0.46

POSITIVE LOGITS

 bezeichneter

0.83

XmlAccessorType

0.81

OGND

0.80

tvguidetime

0.77

 EconPapers

0.76

 Biôgrafia

0.76

RetentionPolicy

0.75

 виправивши

0.74

 initComponents

0.73

 HttpNotFound

0.72

Activations Density 0.159%

references to the pronoun "it."

"it" followed by specific prepositions or verbs

it followed by preposition

No Comments

No Known Activations