INDEX

Explanations

terms related to news and its various formats

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

"News" as the first word

np_acts-logits-general · gemini-2.0-flash

news flash, broadcasting, and updates

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

HOOD

-0.63

aktery

-0.54

UnknownFieldSet

-0.53

yntaxException

-0.53

 Kombat

-0.52

ViewFeatures

-0.51

 صوتيه

-0.50

ContentAlignment

-0.50

anaan

-0.49

Diweddarwch

-0.49

POSITIVE LOGITS

reel

0.74

room

0.74

flash

0.72

feed

0.67

gathering

0.65

rooms

0.64

 onOptions

0.64

 FLASH

0.63

 ""],

0.63

latter

0.63

Activations Density 0.051%

terms related to news and its various formats

"News" as the first word

news flash, broadcasting, and updates

No Comments

No Known Activations