INDEX

Explanations

code snippets about dictionary compilation

oai_token-act-pair · gemini-2.0-flash

Code and foreign language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 незавершена

-0.98

 дописавши

-0.93

 виправивши

-0.89

writeFieldEnd

-0.88



-0.85

 المعيارى

-0.85

 CURLOPT

-0.81

parsedMessage

-0.80

 beginnetje

-0.78

 tartalomajánló

-0.76

POSITIVE LOGITS

的任务

0.56

的学生

0.52

车的

0.52

的车

0.52

的角色

0.52

的孩子

0.50

的朋友

0.49

企业的

0.47

的风

0.47

的产品

0.47

Activations Density 0.134%

code snippets about dictionary compilation

Code and foreign language

No Comments

No Known Activations