INDEX

Explanations

instances of the word "to" with varying significance, indicating a focus on purpose or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-1.00

 NDEBUG

-0.73

ation

-0.70

Namara

-0.68

jetbrains

-0.65

 ilma

-0.64

گیر

-0.64

 sähkö

-0.64

fisher

-0.60

StateChanged

-0.59

POSITIVE LOGITS

to

1.71

TO

1.44

To

1.24

To

1.22

to

1.18

 να

1.11

zu

1.06

TO

1.06

DataTo

1.01

 לה

0.97

Activations Density 1.187%

instances of the word "to" with varying significance, indicating a focus on purpose or intention

No Comments

No Known Activations