INDEX

Explanations

key phrases related to research findings and conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 jScrollPane

-0.86

 calendriers

-0.70

ABUL

-0.66

########.

-0.65

 שוליים

-0.65

 utafitiHapana

-0.63

PageRoute

-0.63

requireNonNull

-0.60

pitre

-0.56

etheless

-0.56

POSITIVE LOGITS

 Majefty

0.80

 تضيفلها

0.77

 poffe

0.76

ſelves

0.72

ſelf

0.72

Datuak

0.71

 houſe

0.70

 purpoſe

0.70

 Jefus

0.69

 uſed

0.68

Activations Density 0.412%

key phrases related to research findings and conclusions

No Comments

No Known Activations