INDEX

Explanations

phrases indicating conditions, exceptions, or stipulations in legal or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

memoized

-0.65

AutoresizingMask

-0.55

enciaga

-0.49

 PopupWindow

-0.49

 BoxDecoration

-0.48

fortawesome

-0.48

ArrowToggle

-0.47

 ControllerBase

-0.47

̣n

-0.45

parsedMessage

-0.45

POSITIVE LOGITS

 otherwise

3.65

otherwise

3.28

Otherwise

3.02

 Otherwise

3.00

 OTHERWISE

2.91

 altrimenti

2.40

 jinak

2.08

 иначе

2.07

 autrement

2.03

不然

1.92

Activations Density 0.383%

phrases indicating conditions, exceptions, or stipulations in legal or formal contexts

No Comments

No Known Activations