INDEX

Explanations

variations of the word 'list'

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

ellee

-0.58

expandindo

-0.56

Hintergrund

-0.56

 CURIAM

-0.54

Whilst

-0.54

таратура

-0.53

ọc

-0.53

Witam

-0.52

wixt

-0.52

/(\

-0.52

POSITIVE LOGITS

 list

2.33

 lists

2.05

 List

1.86

 Lists

1.80

 LIST

1.76

List

1.55

 listes

1.54

 lista

1.54

 liste

1.44

 Liste

1.43

Activations Density 0.074%

variations of the word 'list'

No Comments

No Known Activations