INDEX

Explanations

puncutations and separators within the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

TagMode

-0.95

WebVitals

-0.84

!")

-0.82

 للاسماء

-0.76

.")

-0.73

)");

-0.72

 transférez

-0.72

[])

-0.72

.",

-0.72

")->

-0.71

POSITIVE LOGITS

 regards

1.16

 Regarding

1.12

Regarding

1.09

Regards

1.00

EDIT

1.00

BTW

0.98

 regarding

0.96

Edit

0.94

 EDIT

0.92

Cheers

0.91

Activations Density 0.335%

puncutations and separators within the text

No Known Activations