INDEX

Explanations

first-person present-tense verbs and statements or summaries of viewpoints

oai_token-act-pair · gemini-2.0-flash

Showing empathy

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 فريبيس

-0.85

endphp

-0.71

MemoryWarning

-0.68

KommentareTeilen

-0.58

NameInMap

-0.57

 tartalomajánló

-0.55

HttpFoundation

-0.55

ImageContext

-0.55

 &___

-0.54

pyplot

-0.53

POSITIVE LOGITS

 comforted

0.61

 impressed

0.60

 XXXVII

0.53

 quick

0.53

 moeite

0.53

 reassured

0.51

 attracted

0.50

ElementException

0.50

 gratified

0.50

quick

0.49

Activations Density 1.684%

first-person present-tense verbs and statements or summaries of viewpoints

Showing empathy

No Comments

No Known Activations