INDEX

Explanations

words that end in the letters "ite", "ate", or "dili", along with the words "smo" and "bili", or the phrase "% 1", in the given language snippets

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 ourselves

-1.57

we

-1.18

We

-1.13

our

-1.08

We

-1.07

我們

-1.05

 validamos

-1.02

 我们

-1.02

Нам

-0.99

我们

-0.98

POSITIVE LOGITS

 yours

0.49

yours

0.49

asteroide

0.47

 single

0.46

hens

0.46

 Genius

0.45

 himself

0.45

 mich

0.45

iro

0.44

 gian

0.44

Activations Density 0.263%

words that end in the letters "ite", "ate", or "dili", along with the words "smo" and "bili", or the phrase "% 1", in the given language snippets

No Known Activations