INDEX

Explanations

phrases related to measurements and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Lari

-0.69

🤣🤣

-0.65

Linn

-0.63

ẻo

-0.62

EDR

-0.60

 Petro

-0.58

PDT

-0.58

 Kick

-0.57

 Zacks

-0.57

 neighborhood

-0.57

POSITIVE LOGITS

 upto

1.04

Hasta

1.02

upto

0.98

 ועד

0.95

 atteindre

0.91

Até

0.88

 Até

0.87

 Hasta

0.86

 UNTIL

0.85

iecie

0.84

Activations Density 0.078%

phrases related to measurements and numerical values

No Comments

No Known Activations