INDEX

Explanations

phrases related to changes or fluctuations in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"in the"

np_acts-logits-general · gemini-2.0-flash

increase or decrease of metrics

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</thead>

-0.50



-0.48

 queſta

-0.46

 betweenstory

-0.45

ConstraintMaker

-0.45

 ligiloj

-0.44

ether

-0.44

 Administrativna

-0.42

 mathématiques

-0.42

⅘

-0.42

POSITIVE LOGITS

 decrease

0.66

 Decrease

0.65

Decrease

0.63

 increase

0.59

 disminución

0.59

 Increase

0.58

Increase

0.56

posedge

0.56

 decline

0.55

decrease

0.54

Activations Density 0.748%

phrases related to changes or fluctuations in various contexts

"in the"

increase or decrease of metrics

No Comments

No Known Activations