INDEX

Explanations

occurrences of acronyms, particularly those relevant to medicine or computer science.

oai_token-act-pair · gemini-2.0-flash

MD

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

tvguidetime

-0.73

<bos>

-0.64

 <<<<<<<<<<<<<<

-0.58

 الحره

-0.55

 VIDEOTAPE

-0.52

unek

-0.52

 Cassini

-0.51

脚注の使い方

-0.50

ValueStyle

-0.50

__((

-0.50

POSITIVE LOGITS

 betweenstory

0.61

antMatchers

0.56

blurRadius

0.56

CWE

0.55

ArrowToggle

0.55

bootstrapcdn

0.48

Geplaatst

0.47

 hendes

0.46

EDEFAULT

0.46

contentLoaded

0.45

Activations Density 34.494%

occurrences of acronyms, particularly those relevant to medicine or computer science.

MD

No Comments

No Known Activations