INDEX

Explanations

phrases indicating immediate and significant changes or effects, particularly related to economics and societal impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Autoritní

-0.89

Viitteet

-0.60

 externi

-0.58

SequentialGroup

-0.56

تقاوى

-0.55

starts

-0.55

Lähteet

-0.55

談社

-0.54

 mema

-0.54

replaced

-0.50

POSITIVE LOGITS

 increase

1.25

 decrease

1.07

 change

1.04

 rise

1.02

 shift

1.00

 jump

0.97

 reduction

0.95

 decline

0.92

 drop

0.91

 spike

0.89

Activations Density 0.742%

phrases indicating immediate and significant changes or effects, particularly related to economics and societal impacts

No Comments

No Known Activations