INDEX

Explanations

instances of the word "Then."

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

 leſs

-0.70

 poffe

-0.69

ChildScrollView

-0.65

 $\$$

-0.63

"""

-0.61

 ſeveral

-0.60

 endforeach

-0.59

 whoſe

-0.59

 perfons

-0.59

</table>

-0.59

POSITIVE LOGITS

 Then

1.32

Then

1.25

 THEN

1.20

THEN

1.11

 then

0.99

then

0.87

 puis

0.78

 Followed

0.78

Worse

0.77

 Потом

0.75

Activations Density 0.155%

instances of the word "Then."

No Comments

No Known Activations