INDEX

Explanations

conversational phrases and expressions indicating uncertainty or questioning

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

Japanese sentence fragments/endings

np_acts-logits-general · gemini-2.0-flash

Japanese sentence endings like questions or statements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 itſelf

-1.12

 myſelf

-1.07

TintMode

-1.06

 }}"></

-1.03

DockStyle

-1.03

 doubtnut

-1.02

 betweenstory

-0.96

setVerticalGroup

-0.94

 pleaſure

-0.94

SharedCtor

-0.93

POSITIVE LOGITS

0.67

...

0.59

or

0.56

…

0.55

0.53

0.52

 that

0.51

to

0.50

 because

0.49

Activations Density 0.038%

conversational phrases and expressions indicating uncertainty or questioning

Japanese sentence fragments/endings

Japanese sentence endings like questions or statements

No Comments

No Known Activations