INDEX

Explanations

numerical values associated with measurements and conversions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 ModelExpression

-0.89

 ویکی‌پدیای

-0.87

webElementXpaths

-0.87

كذا

-0.76

=$?

-0.75

 oprot

-0.73

:✨

-0.72

 uſed

-0.69

SharedDtor

-0.68

 leſs

-0.67

POSITIVE LOGITS

SequentialGroup

0.54

 ReactDOM

0.50

ResponseEntity

0.49

ox

0.48

jeeling

0.47

eter

0.46

0.45

anine

0.45

np

0.44

np

0.44

Activations Density 0.018%

numerical values associated with measurements and conversions

No Comments

No Known Activations