INDEX

Explanations

commands or keywords related to editing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.75

getInstance

-0.68

 getInstance

-0.68

พาะ

-0.66

ceaux

-0.66

 McCormick

-0.65

 cocos

-0.65

backgroundColor

-0.65

 porcelaine

-0.64

ova

-0.63

POSITIVE LOGITS

Dit

1.05

dit

1.02

 Edit

1.01

 EDIT

0.97

Edit

0.96

Dit

0.92

 CHAT

0.90

udit

0.86

 edit

0.85

EDIT

0.85

Activations Density 0.047%

commands or keywords related to editing functions

No Comments

No Known Activations