INDEX

Explanations

mentions of the word "pe" or its variants as part of different phrases

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

 bezeichneter

-0.65

 Stä

-0.64

Ley

-0.63

Rory

-0.60

 tartalomajánló

-0.60

 collateral

-0.60

 Norris

-0.59

ximate

-0.56

SetOutput

-0.56

Ley

-0.56

POSITIVE LOGITS

Pe

2.93

Pe

2.81

pe

2.79

pe

2.71

PE

2.22

PE

2.16

 Peep

1.64

 peels

1.52

 Peta

1.51

Pee

1.50

Activations Density 0.079%

mentions of the word "pe" or its variants as part of different phrases

No Comments

No Known Activations