INDEX

Explanations

symbols or formatting indicators used in technical writing

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

Text after an asterisk

np_acts-logits-general · gemini-2.0-flash

words following asterisk

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

endphp

-0.87

 CreateTagHelper

-0.84

ViewFeatures

-0.81

#+#

-0.80

клопе

-0.78

 getItemId

-0.78

 ویکی‌پدی

-0.77

 ་་

-0.75

drawSprites

-0.74

-0.73

POSITIVE LOGITS

Note

0.89

0.75

note

0.73

The

0.69

NOTE

0.68

 Note

0.68

 note

0.64

Please

0.63

 What

0.60

This

0.59

Activations Density 0.255%

symbols or formatting indicators used in technical writing

Text after an asterisk

words following asterisk

No Comments

No Known Activations