INDEX

Explanations

key health-related metrics and conditions

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

"The" followed by a positive word

np_acts-logits-general · gemini-2.0-flash

the + opportunity/potential/degree

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 denen

-0.53

 cauza

-0.49

 című

-0.46

 those

-0.45

 otomatig

-0.44

หาร

-0.44

 illustrazione

-0.43

väg

-0.42

 appena

-0.42

 jakie

-0.42

POSITIVE LOGITS

 ability

0.90

 capability

0.84

 opportunity

0.83

 added

0.81

 option

0.81

 foresight

0.80

 benefit

0.79

 advantage

0.78

added

0.77

benefit

0.76

Activations Density 0.244%

key health-related metrics and conditions

"The" followed by a positive word

the + opportunity/potential/degree

No Comments

No Known Activations