INDEX

Explanations

instances of the word "to" used 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

jména

-0.79

ation

-0.66

pośred

-0.64

fisher

-0.64

 ilma

-0.63

 NDEBUG

-0.62

 Behav

-0.62

 sähkö

-0.61

Switcher

-0.60

Calla

-0.60

POSITIVE LOGITS

to

1.25

TO

1.22

zu

1.01

AddTagHelper

0.98

TO

0.96

To

0.95

To

0.95

 CreateTagHelper

0.92

yto

0.91

 να

0.90

Activations Density 1.175%

instances of the word "to" used in various contexts

No Comments

No Known Activations