INDEX

Explanations

questions starting with "Are" indicating inquiry or requests for information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

wieś

-0.72

allero

-0.57

 Söhne

-0.57

 following

-0.56

ilerini

-0.56

fieldLabel

-0.56

 ziren

-0.56

 Johnstone

-0.55

“

-0.55

 respective

-0.54

POSITIVE LOGITS

Are

2.07

Are

2.06

ARE

1.76

are

1.62

ARE

1.43

 Aren

1.18

Aren

1.07

Area

0.97

 areal

0.83

aren

0.79

Activations Density 0.088%

questions starting with "Are" indicating inquiry or requests for information

No Comments

No Known Activations