INDEX

Explanations

mentions of people and their actions, possibly in a legal or political context

oai_token-act-pair · gemini-2.0-flash

legal/political disputes

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

 незавершена

-0.98

 himself

-0.97

himself

-0.94

parsedMessage

-0.94

 насељу

-0.88

 kasarigan

-0.87

 CreateTagHelper

-0.85

 myſelf

-0.85

Rhestr

-0.85

 NSCoder

-0.85

POSITIVE LOGITS

its

0.54

we

0.50

шло

0.50

brunn

0.48

 assoluto

0.44

お互

0.44

 stalo

0.44

相互

0.44

 familles

0.43

Activations Density 3.657%

mentions of people and their actions, possibly in a legal or political context

legal/political disputes

No Comments

No Known Activations