INDEX

Explanations

statements expressing opinions or preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

-0.51

enterOuterAlt

-0.50

 kohdetta

-0.48

лтемелер

-0.45

 fieldNum

-0.41

 parseFrom

-0.40

 دیکھیے

-0.39

oriques

-0.39

ungguh

-0.37

fromnode

-0.36

POSITIVE LOGITS

 better

3.11

better

2.84

Better

2.72

 Better

2.61

 mejor

2.59

 лучше

2.34

 melhor

2.33

 BETTER

2.25

 meglio

2.25

 mieux

2.20

Activations Density 0.637%

statements expressing opinions or preferences

No Comments

No Known Activations

statements expressing opinions or preferences

No Comments

No Known Activations