INDEX

Explanations

references to 'the' or similar definite articles in various contexts

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

Followed by different nouns

np_acts-logits-general · gemini-2.0-flash

the followed by noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

BeforeAll

-0.53

mybatisplus

-0.47

GoogleApiClient

-0.47

ponym

-0.46

 amus

-0.46

 fièvre

-0.44

aş

-0.44

 kids

-0.44

UnitTesting

-0.44

veld

-0.43

POSITIVE LOGITS

 lack

0.75

 advent

0.73

 ability

0.73

 availability

0.69

StructEnd

0.69

RectangleBorder

0.67

 amount

0.66

何より

0.66

发表于

0.66

">//

0.66

Activations Density 0.564%

references to 'the' or similar definite articles in various contexts

Followed by different nouns

the followed by noun

No Comments

No Known Activations