INDEX

Explanations

phrases related to improvements and advancements beyond current standards or practices

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

comparison or contrast

np_acts-logits-general · gemini-2.0-flash

beyond or transcending something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

both

-0.63

 both

-0.61

 begge

-0.61

 entrambi

-0.60

 similaires

-0.59

 zowel

-0.57

Both

-0.56

 inoltre

-0.55

 både

-0.55

 mesmo

-0.55

POSITIVE LOGITS

 selve

1.35

 actual

1.28

 непосредственно

1.26

 physical

1.16

 eigentlichen

1.10

 directly

1.07

 själva

1.07

 immediate

1.06

actual

1.06

 direct

1.05

Activations Density 0.563%

phrases related to improvements and advancements beyond current standards or practices

comparison or contrast

beyond or transcending something

No Comments

No Known Activations