INDEX

Explanations

references to "the" in a variety of contexts

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

"the" followed by an adjective

np_acts-logits-general · gemini-2.0-flash

the specific thing

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

 resourceCulture

-0.79

httphttps

-0.67

 betweenstory

-0.63

Personensuche

-0.62

各

-0.62

 flesta

-0.60

schemes

-0.60

ismet

-0.59

 ellers

-0.56

 fleste

-0.56

POSITIVE LOGITS

 only

0.98

 same

0.89

 easiest

0.85

 epitome

0.82

 perfect

0.81

 result

0.78

 reason

0.77

 least

0.77

 thing

0.76

 quickest

0.73

Activations Density 0.238%

references to "the" in a variety of contexts

"the" followed by an adjective

the specific thing

No Comments

No Known Activations