INDEX

Explanations

forms of the verb "to be."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SIN

-0.59

 pouvoirs

-0.58

 oleju

-0.57

žin

-0.56

 Heizung

-0.56

wasn

-0.56

 neuem

-0.55

ubehör

-0.55

SIZ

-0.54

axel

-0.54

POSITIVE LOGITS

are

1.53

 yourselves

1.34

 themselves

1.33

 were

1.31

ARE

1.29

themselves

1.23

 WERE

1.19

were

1.18

Are

1.15

 Were

1.15

Activations Density 0.466%

forms of the verb "to be."

No Comments

No Known Activations