INDEX

Explanations

phrases used to discuss the pros and cons of medical issues

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 esternos

-0.65

GHIJKLM

-0.58

 AssemblyCulture

-0.49

 lest

-0.48

quate

-0.48

 الحره

-0.47

adaş

-0.47

__*/

-0.46

Skocz

-0.44

انجليز

-0.44

POSITIVE LOGITS

 benefits

2.47

 benefit

2.39

benefit

2.14

benefits

2.13

Benefit

2.09

 Benefits

2.09

Benefits

2.03

 Benefit

2.03

 BENEFITS

1.96

 benefited

1.80

Activations Density 1.823%

phrases used to discuss the pros and cons of medical issues

No Known Activations