INDEX

Explanations

words indicating an externally imposed status or label

oai_token-act-pair · gemini-2.0-flash

mark

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

marking

-0.94

 tagging

-0.90

 labels

-0.90

 Label

-0.90

 marking

-0.88

 tags

-0.88

 Labels

-0.88

 Marking

-0.86

 tagged

-0.86

tag

-0.84

POSITIVE LOGITS

 bénéficiaire

0.50

исленность

0.46

articolo

0.45

χαν

0.42

ضير

0.41

秋冬

0.41

ítása

0.40

 suspens

0.40

antenimiento

0.40

anglicky

0.40

Activations Density 9.913%

words indicating an externally imposed status or label

mark

No Comments

No Known Activations