INDEX

Explanations

the word "according."

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

łość

-0.64

 alfo

-0.64

ŚĆ

-0.63

конец

-0.63

Външни

-0.63

ệc

-0.61

CMP

-0.61

lectricité

-0.60

felves

-0.59

afficheront

-0.59

POSITIVE LOGITS

Según

1.40

 Según

1.35

Selon

1.33

 Selon

1.29

According

1.25

 Secondo

1.24

Secondo

1.23

according

1.19

 according

1.19

 לפי

1.19

Activations Density 0.083%

the word "according."

No Comments

No Known Activations