INDEX

Explanations

the letter 'E' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

égard

-0.65

.*")]

-0.63

جراء

-0.59

lot

-0.58

 currentIndex

-0.57

"}")

-0.57

ambassade

-0.57

Empereur

-0.56

IVEREF

-0.55

 setUser

-0.55

POSITIVE LOGITS

0.64

0.51

 resourceCulture

0.49

Е

0.47

exact

0.47

 ActiveRecord

0.46

UnusedPrivate

0.46

 exact

0.44

 gamle

0.44

Activations Density 0.215%

the letter 'E' in various contexts

No Comments

No Known Activations