INDEX

Explanations

the beginning of sentences or passages, typically marked by a specific token indicating the start of a new section

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

__).

-0.49

($"{

-0.48

">//

-0.45

kom

-0.44

vated

-0.43

klo

-0.42

 tend

-0.42

-0.41

[]>(

-0.41

POSITIVE LOGITS

تقاوى

1.03

IsContent

0.98

writeField

0.92

tagHelperRunner

0.86

DockStyle

0.85

 quæ

0.83

 الرياضيه

0.80

 ejus

0.79

 ویکی‌پدیا

0.79

EndContext

0.78

Activations Density 0.045%

the beginning of sentences or passages, typically marked by a specific token indicating the start of a new section

No Known Activations