INDEX

Explanations

phrases related to opinions and subjective judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 itſelf

-1.10

Efq

-1.08

InputBorder

-1.05

 myſelf

-1.04

 houſe

-1.00

Eſ

-0.99

 ſtate

-0.99

 uſed

-0.99

 whoſe

-0.98

 Houſe

-0.96

POSITIVE LOGITS

0.52

documentElement

0.44

↵

0.43

 biji

0.42

 ujednoznacz

0.40

be

0.40

 reves

0.39

imen

0.38

IX

0.38

נית

0.38

Activations Density 1.353%

phrases related to opinions and subjective judgments

No Comments

No Known Activations