INDEX

Explanations

instances of the word "highlight" or variations of it, indicating an emphasis on significant points or features within the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

SequentialGroup

-0.73

 صوتيه

-0.72

ClientSize

-0.66

 Infine

-0.65

zzleHttp

-0.65

 CGSize

-0.64

 useAuth

-0.63

 vallée

-0.63

BagLayout

-0.62

 Kieran

-0.62

POSITIVE LOGITS

 highlight

1.36

 Highlight

1.20

Highlight

1.13

 highlights

1.10

highlights

1.06

 Highlights

1.00

Highlights

0.99

highlight

0.95

 sight

0.91

 Sight

0.90

Activations Density 0.071%

instances of the word "highlight" or variations of it, indicating an emphasis on significant points or features within the text

No Comments

No Known Activations