INDEX

Explanations

words and phrases related to mechanics, electronics and engineering

oai_token-act-pair · gemini-2.0-flash

code/technical forum posts

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

awarkan

-0.52

 affich

-0.51

 verteilt

-0.50

 consta

-0.50

 caída

-0.48

 hålla

-0.47

ställ

-0.47

gaande

-0.47

 lära

-0.47

 ensayos

-0.45

POSITIVE LOGITS

########.

0.66

}))

0.66

 '\\;'

0.65

]")]

0.59

PRNewswire

0.58

AddTagHelper

0.57

 Allociné

0.57

pielt

0.55

inander

0.54

原始内容存档于

0.53

Activations Density 0.971%

words and phrases related to mechanics, electronics and engineering

code/technical forum posts

No Comments

No Known Activations