INDEX

Explanations

negation expressions or phrases that indicate a condition is not met

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.54

and

-0.51

’

-0.49

 renta

-0.49

 might

-0.49

-0.48

ing

-0.48

 family

-0.47

clientY

-0.47

POSITIVE LOGITS

(!

1.73

(!__

1.54

(!

1.45

(!_

1.16

 تضيفلها

1.16

((!

1.15

{!

1.13

{!

1.13

 Normdatei

1.05

GraphicsUnit

1.05

Activations Density 0.017%

negation expressions or phrases that indicate a condition is not met

No Comments

No Known Activations