INDEX

Explanations

references to majority opinion or rule

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

</i>

-0.79

']?>

-0.77

 videre

-0.70

zah

-0.69

 Croft

-0.66

yakit

-0.65

 Arte

-0.64

skis

-0.64

Dates

-0.63

Arte

-0.63

POSITIVE LOGITS

 majority

1.53

 Majority

1.43

Majority

1.42

majority

1.41

ority

1.03

 Majefty

0.99

 myſelf

0.95

 minority

0.95

 تضيفلها

0.94

 purpoſe

0.93

Activations Density 0.098%

references to majority opinion or rule

No Comments

No Known Activations