INDEX

Explanations

instances of summarization or major highlights within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

postmedia

-0.53

 pouvoirs

-0.51

adə

-0.50

 kapcs

-0.49

 âgées

-0.49

berdayakan

-0.48

 piatta

-0.48

ihnachten

-0.48

 elettrico

-0.47

político

-0.47

POSITIVE LOGITS

":[{

0.68

:✨

0.60

webElement

0.58

TemporalType

0.57

 الحره

0.56

__()

0.55

 sacco

0.55

 interactive

0.54

 snack

0.53

 multimedia

0.52

Activations Density 0.173%

instances of summarization or major highlights within a text

No Comments

No Known Activations