INDEX

Explanations

patterns of structured data or specific formatting elements

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

<bos>

-2.73

 المعيارى

-1.22

 Савезне

-1.20

########.

-0.98

’

-0.96

 ujednoznacz

-0.95

 समीक्षक

-0.94

-0.93

 AspNetCore

-0.93

 виправивши

-0.91

POSITIVE LOGITS

0.50

0.49

ене

0.44

фов

0.44

“

0.43

â

0.43

0.42

omb

0.42

0.41

Activations Density 0.475%

patterns of structured data or specific formatting elements

No Comments

No Known Activations