INDEX

Explanations

references to editing actions or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

-1.02

oporosis

-0.73

 getInstance

-0.69

 cocos

-0.68

إنه

-0.67

columnNumber

-0.65

ônes

-0.65

 AppModule

-0.65

Boxscore

-0.65

myArray

-0.64

POSITIVE LOGITS

 Edit

1.55

Edit

1.49

 edit

1.47

 EDIT

1.43

edit

1.36

EDIT

1.23

 Edits

1.14

isEdit

1.10

Dit

1.06

 edits

1.05

Activations Density 0.056%

references to editing actions or commands

No Comments

No Known Activations