INDEX

Explanations

Japanese particles and sentence structure indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Monfieur

-0.93

 Jefus

-0.91

 houſe

-0.91

 itſelf

-0.91

 poffible

-0.90

 Chriftian

-0.86

 reaſon

-0.86

 iſt

-0.84

Efq

-0.84

 purpoſe

-0.84

POSITIVE LOGITS

を

1.15

을

1.08

みを

1.04

子を

1.03

를

1.00

曲を

0.98

いを

0.98

devamını

0.95

を

0.92

를

0.90

Activations Density 0.022%

Japanese particles and sentence structure indicators

No Comments

No Known Activations