INDEX

Explanations

action verbs related to instructions for preparing food or assembling items

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

Text following the word "the"

np_acts-logits-general · gemini-2.0-flash

the followed by a noun

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

 recientes

-0.51

 ujednoznacz

-0.51

 confirmé

-0.48

quakes

-0.47

 meille

-0.46

 entendido

-0.45

 traduc

-0.43

 recentes

-0.43

 obligado

-0.43

 Pilate

-0.43

POSITIVE LOGITS

 edges

0.79

XmlAccessorType

0.71

SpringBootTest

0.69

 entire

0.69

 ENTIRE

0.68

yntaxException

0.67

 corners

0.67

 contents

0.67

GOTREF

0.66

 unit

0.64

Activations Density 0.638%

action verbs related to instructions for preparing food or assembling items

Text following the word "the"

the followed by a noun

No Comments

No Known Activations