INDEX

Explanations

phrases indicating quantities or limits

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

APORE

-0.68

 Pingback

-0.59

GLC

-0.57

ODS

-0.56

 Hake

-0.56

 dissoci

-0.55

vin

-0.55

PSA

-0.55

NOC

-0.55

 pprint

-0.55

POSITIVE LOGITS

 upto

1.13

upto

1.05

Hasta

0.97

 hasta

0.87

 Hasta

0.87

hasta

0.82

 Hingga

0.81

awtextra

0.81

 Até

0.80

Até

0.79

Activations Density 0.104%

phrases indicating quantities or limits

No Comments

No Known Activations