INDEX

Explanations

phrases or words that indicate an increase or emphasis, particularly in relation to quantities or frequency

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

"More" followed by a comparative word/phrase

np_acts-logits-general · gemini-2.0-flash

more than

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(&:

-0.77

bufio

-0.72

IndentedString

-0.70

 ImageIcon

-0.70

️

-0.67

styrelsen

-0.65

johtaja

-0.64

 NgModule

-0.63

 Révolution

-0.62

GenerationType

-0.61

POSITIVE LOGITS

 than

1.61

than

1.12

 THAN

1.09

Than

1.08

 Than

1.02

 niż

1.00

 more

0.90

 MORE

0.90

THAN

0.89

 Moreira

0.87

Activations Density 0.182%

phrases or words that indicate an increase or emphasis, particularly in relation to quantities or frequency

"More" followed by a comparative word/phrase

more than

No Comments

No Known Activations