INDEX

Explanations

references to content management and loading operations in code

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

)));

-0.46

 verlo

-0.45

Distinctions

-0.44

 thư

-0.44

 swag

-0.43

воды

-0.43

thol

-0.42

 edifice

-0.42

 Empieza

-0.42

POC

-0.41

POSITIVE LOGITS

تقاوى

0.80

richTextPanel

0.67

 المعيارى

0.66

AutoScaleMode

0.66

TagMode

0.65

 PublicKey

0.64

ValueStyle

0.62

 kaarangay

0.62

انيف

0.62

Geplaatst

0.61

Activations Density 0.037%

references to content management and loading operations in code

No Comments

No Known Activations