INDEX

Explanations

forms of the word "which."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ArrowToggle

-0.86

 utafitiHapana

-0.75

ngoing

-0.58

 kasarigan

-0.56

 propOrder

-0.56

Euer

-0.55

Portale

-0.54

libft

-0.53

 Flames

-0.53

 Euer

-0.53

POSITIVE LOGITS

 which

1.36

which

1.25

 Which

1.24

Which

1.22

 WHICH

1.10

hich

0.95

 wich

0.91

ซึ่ง

0.85

 lequel

0.76

 οποίο

0.75

Activations Density 0.273%

forms of the word "which."

No Comments

No Known Activations