INDEX

Explanations

a verb followed by "a" and a noun or adjective

oai_token-act-pair · gemini-2.0-flash

a

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Przypisy

-0.65

AutoScale

-0.59

SequentialGroup

-0.56

contentLoaded

-0.56

LikeLike

-0.51

DataAnnotations

-0.51

 carottes

-0.50

 pitié

-0.49

 devoirs

-0.49

 оригіналу

-0.47

POSITIVE LOGITS

__.__

0.60

URDAY

0.59

NOPQRST

0.58

ophenol

0.56

dataclass

0.56

SOUNDBITE

0.56

UrlResolution

0.55

 Flan

0.55

 clearColor

0.55

okin

0.53

Activations Density 0.974%

a verb followed by "a" and a noun or adjective

a

No Comments

No Known Activations