INDEX

Explanations

specific characters or symbols, particularly in the context of pricing or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

"}")

-0.53

مراجع

-0.51

ributor

-0.50

LElement

-0.50

rlpool

-0.48

╰

-0.48

nthesis

-0.48

simmon

-0.47

ifoli

-0.46

mbad

-0.43

POSITIVE LOGITS

contentLoaded

0.75

WithIOException

0.67

findpost

0.66

 Mercurio

0.66

########.

0.65

 jScrollPane

0.64

wpi

0.63

 صوتيه

0.62

 edelstahl

0.61

HasAnnotation

0.60

Activations Density 0.155%

specific characters or symbols, particularly in the context of pricing or measurements

No Comments

No Known Activations