INDEX

Explanations

instances of the word "quite."

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

KeySpec

-0.73

 flèche

-0.72

 Alvarado

-0.69

gdx

-0.66

 Berman

-0.65

 Flanagan

-0.65

/////////////

-0.64

 culturelles

-0.63

 Dooley

-0.60

 berlina

-0.59

POSITIVE LOGITS

 quite

3.04

quite

2.92

 Quite

2.76

Quite

2.70

 uite

1.64

 ganske

1.32

 bastante

1.23

 fairly

1.16

 khá

1.11

 Fairly

1.06

Activations Density 0.055%

instances of the word "quite."

No Comments

No Known Activations