INDEX

Explanations

mentions of legal systems, politics, or names of people associated with one or the other, along with their associated adjectives and titles

oai_token-act-pair · gemini-2.0-flash

Affirmative action, voice

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 xrange

-0.61

AtIndexPath

-0.52

iTunes

-0.50

Legături

-0.50

inescent

-0.50

ulka

-0.49

❉

-0.48

Obama

-0.47

 iTunes

-0.47

റ്

-0.47

POSITIVE LOGITS

aarrggbb

0.73

 ChatGPT

0.73

 دیکھیے

0.69

StandardCharsets

0.68

 "..\..\..\

0.68

 metaverse

0.67

UnusedPrivate

0.65

 omicron

0.65

MemoryWarning

0.65

0.64

Activations Density 0.697%

mentions of legal systems, politics, or names of people associated with one or the other, along with their associated adjectives and titles

Affirmative action, voice

No Comments

No Known Activations