INDEX

Explanations

phrases related to interactions within a group context

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

CustomAttributes

-0.47

hely

-0.47

位

-0.47

walde

-0.46

 occupancy

-0.46

 mandat

-0.45

Hot

-0.45

 indic

-0.45

craig

-0.44

hot

-0.44

POSITIVE LOGITS

 виправивши

0.73

 purpoſe

0.73

+:+

0.70

 wikipagina

0.66

 greateſt

0.64

StoryboardSegue

0.64

coroutines

0.64

basicConfig

0.63

 isComment

0.63

 houſe

0.63

Activations Density 0.392%

phrases related to interactions within a group context

No Comments

No Known Activations