INDEX

Explanations

affirmative responses or expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Datuak

-0.70

 setObject

-0.69

iect

-0.67

المناصب

-0.65

+#+#

-0.65

OIR

-0.64

Ng

-0.63

بوابة

-0.62

antium

-0.62

zak

-0.61

POSITIVE LOGITS

 poffe

1.03

 Bacteriol

1.02

 ſche

1.01

 lookin

1.00

 GONNA

0.99

 himſelf

0.98

 outta

0.97

 kids

0.97

 purpoſe

0.97

 ſtate

0.94

Activations Density 0.076%

affirmative responses or expressions of agreement

No Comments

No Known Activations