INDEX

Explanations

present tense verbs and associated sentence structures

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

 would

-0.55

-0.53

we

-0.48

 line

-0.48

’

-0.47

 were

-0.47

 weren

-0.46

Mc

-0.46

”

-0.45

POSITIVE LOGITS

 itſelf

1.08

 Forumite

0.96

 ſmall

0.96

 thiệu

0.95

 whoſe

0.93

 becauſe

0.91

 Theſe

0.91

InjectAttribute

0.91

 himſelf

0.90

NameInMap

0.89

Activations Density 0.082%

present tense verbs and associated sentence structures

No Comments

No Known Activations