INDEX

Explanations

references to the letter 'T' or words starting with 'T'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

om

-0.66

op

-0.52

ag

-0.51

ra

-0.49

ile

-0.48

 moks

-0.48

hou

-0.47

hat

-0.47

ype

-0.47

han

-0.47

POSITIVE LOGITS

 jScrollPane

0.70

parsedMessage

0.69

 صوتيه

0.65

RetentionPolicy

0.63

providedIn

0.63

 Formosa

0.60

 Seer

0.60

 locket

0.59

 woodpecker

0.57

verständlich

0.57

Activations Density 0.212%

references to the letter 'T' or words starting with 'T'

No Comments

No Known Activations