INDEX

Explanations

'ity'

np_token-act-pair-logits · gemini-2.0-flash

positive product reviews with intensifying adverbs

oai_token-act-pair · gemini-2.0-flash

Endings

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 propOrder

-0.93

SharedCtor

-0.90

تقاوى

-0.84

#+#

-0.84

IndentedString

-0.80

 Chwiliwch

-0.80

Vidite

-0.76

存于互联网档案馆

-0.74

LEncoder

-0.74

 Administrativna

-0.74

POSITIVE LOGITS

ity

0.47

 complexity

0.47

ry

0.47

Ouv

0.46

ory

0.46

ORY

0.45

 operating

0.44

iter

0.44

 asing

0.43

 Operating

0.43

Activations Density 1.067%

'ity'

positive product reviews with intensifying adverbs

Endings

No Comments

No Known Activations