INDEX

Explanations

the beginning of a new document

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

Text followed by numbers

np_acts-logits-general · gemini-2.0-flash

numbers, alphanumeric characters, and specialized terms

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

 last

-0.67

 recent

-0.66

 later

-0.64

-0.59

 recently

-0.57

去年

-0.56

last

-0.56

昨年

-0.51

 recente

-0.50

 yesterday

-0.50

POSITIVE LOGITS

 utafitiHapana

1.07

setVerticalGroup

0.95

styleType

0.94

ValueStyle

0.93

Hentet

0.93

تقاوى

0.91

extAlignment

0.89

 المعيارى

0.87

TagMode

0.81

 مشين

0.81

Activations Density 0.067%

the beginning of a new document

Text followed by numbers

numbers, alphanumeric characters, and specialized terms

No Comments

No Known Activations