INDEX

Explanations

mentions of IT related troubleshooting.

oai_token-act-pair · gemini-2.0-flash

Negative conjunctions/adverbs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.63

)}</

-0.63

MLLoader

-0.62

?')

-0.59

\{\\

-0.58

ņš

-0.57

,:),

-0.56

 EconPapers

-0.54

 متعلقه

-0.53

Revenir

-0.53

POSITIVE LOGITS

nor

1.62

 anymore

1.27

nor

1.20

Nor

1.13

 neither

1.11

neither

1.08

Nor

1.07

 nici

1.03

 Neither

0.99

 unless

0.98

Activations Density 21.157%

mentions of IT related troubleshooting.

Negative conjunctions/adverbs

No Comments

No Known Activations