INDEX

Explanations

phrases that indicate significant announcements or events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 useAuth

-0.54

cuerdo

-0.52

mbggenerated

-0.50

씩

-0.48

 Résultat

-0.47

HEP

-0.47

Bedankt

-0.46

createCanvas

-0.46

calyptic

-0.45

 occasional

-0.45

POSITIVE LOGITS

 shortly

1.49

 Shortly

1.18

Shortly

1.17

 justo

1.11

 before

1.05

 coincided

1.02

 BEFORE

1.02

 preceded

1.01

 coincident

1.00

 just

0.97

Activations Density 0.487%

phrases that indicate significant announcements or events and their implications

No Comments

No Known Activations