INDEX

Explanations

references to water and its properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hdashline

-0.90

 Sabina

-0.87

BeginContext

-0.86

iibo

-0.84

 myſelf

-0.84

 mẽ

-0.81

 tartalomajánló

-0.79

},[])

-0.79

zbęd

-0.78

 Clamp

-0.78

POSITIVE LOGITS

 water

1.47

 Water

1.45

Water

1.41

water

1.35

 WATER

1.33

WATER

1.29

 waters

1.20

 Waters

1.17

Waters

1.13

 Wasser

1.09

Activations Density 0.051%

references to water and its properties

No Comments

No Known Activations