INDEX

Explanations

instances of the article "a."

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

"A" followed by a noun

np_acts-logits-general · gemini-2.0-flash

quantifiers after "a"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 amitié

-0.99

 affrontare

-0.96

 autorité

-0.94

 armée

-0.92

 école

-0.91

 aumentare

-0.90

 équipe

-0.89

 avere

-0.89

 église

-0.89

 âge

-0.89

POSITIVE LOGITS

few

0.93

lot

0.91

 couple

0.75

 variety

0.66

 handful

0.64

 bunch

0.63

 series

0.61

 pair

0.61

 multitude

0.61

 number

0.61

Activations Density 1.002%

instances of the article "a."

"A" followed by a noun

quantifiers after "a"

No Comments

No Known Activations

instances of the article "a."

"A" followed by a noun

quantifiers after "a"

No Comments

No Known Activations