INDEX

Explanations

the word 'the' and words that often proceed it

oai_token-act-pair · gemini-2.0-flash

Text excerpts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Rhestr

-0.62

 Administrativna

-0.55

 المعيارى

-0.51

########.

-0.51

TargetException

-0.49

 établissements

-0.48

Демографія

-0.47

 rosin

-0.47

Carreira

-0.47

 MenuView

-0.45

POSITIVE LOGITS

SequentialGroup

0.71

 Smiths

0.69

hasis

0.64

cys

0.62

eses

0.61

ises

0.60

bens

0.59

kreises

0.59

 Indias

0.59

usses

0.59

Activations Density 0.880%

the word 'the' and words that often proceed it

Text excerpts

No Comments

No Known Activations