INDEX

Explanations

phrases expressing certainty or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Autoritní

-0.83

:✨

-0.68

 betweenstory

-0.62

TextAppearance

-0.62

 Mahomet

-0.60

Бахар

-0.60

PreInfinity

-0.58

 Busse

-0.58

EDEFAULT

-0.57

 snippetHide

-0.57

POSITIVE LOGITS

__((

0.64

AspNet

0.55

Enfant

0.47

can

0.47

 naturally

0.47

)__

0.46

 vastaan

0.45

 possible

0.44

┳

0.43

깐

0.43

Activations Density 0.621%

phrases expressing certainty or potential outcomes

No Comments

No Known Activations