INDEX

Explanations

phrases indicating negativity or criticism

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

"There's" or "There is"

np_acts-logits-general · gemini-2.0-flash

There's no

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ſame

-0.63

 betweenstory

-0.60

 considérons

-0.57

 houſe

-0.56

ThemeOverlay

-0.55

 Ibid

-0.54

 кӀош

-0.53

transQ

-0.52

nikova

-0.50

️

-0.50

POSITIVE LOGITS

 nothing

1.00

 certainly

0.82

nothing

0.80

 definitely

0.80

 always

0.77

Nothing

0.75

 NOTHING

0.70

 plenty

0.69

 lots

0.69

 Nothing

0.68

Activations Density 0.078%

phrases indicating negativity or criticism

"There's" or "There is"

There's no

No Comments

No Known Activations