INDEX

Explanations

references to a specific author or reference marked with 'T'

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

Tokens after the letter "T"

np_acts-logits-general · gemini-2.0-flash

T followed by certain names

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

 invokevirtual

-0.60

apatalk

-0.59

mybatisplus

-0.57

biotics

-0.57

terbury

-0.53

pairs

-0.53

 Polícia

-0.51

Foreword

-0.50

biology

-0.50

yskland

-0.49

POSITIVE LOGITS

 otomatig

0.59

 }}"></

0.58

Personendaten

0.56

vidad

0.56

blind

0.56

itulo

0.53

évaluateur

0.53

ostante

0.53

protoimpl

0.51

férences

0.51

Activations Density 0.149%

references to a specific author or reference marked with 'T'

Tokens after the letter "T"

T followed by certain names

No Comments

No Known Activations