INDEX

Explanations

words for emphasis and qualification like comparatives, conjunctions, specifiers, degrees of certainty, and references to texts

oai_token-act-pair · gemini-2.0-flash

intensifiers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.56

]--;

-0.53

 Himo

-0.48

Geplaatst

-0.47

vestream

-0.47

طلحات

-0.43

 Rept

-0.42

xture

-0.41

 handed

-0.41

WIP

-0.41

POSITIVE LOGITS

Tembelea

0.71

InlineData

0.68

 ویکی‌پدیا

0.61

getColumnIndex

0.57

numerusform

0.55

ழ்

0.52

tamol

0.52

BagConstraints

0.51

gdx

0.51

 Vogt

0.50

Activations Density 15.097%

words for emphasis and qualification like comparatives, conjunctions, specifiers, degrees of certainty, and references to texts

intensifiers

No Comments

No Known Activations