INDEX

Explanations

instances of timestamps or temporal markers

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

Preposition "to" followed by a word

np_acts-logits-general · gemini-2.0-flash

to + number or unit of measure

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.78

 Sarm

-0.67

 themſelves

-0.67

 Pelop

-0.65

 Mahomet

-0.65

 Anſ

-0.65

 eiffel

-0.64

Efq

-0.64

 Shakspeare

-0.62

 Cupid

-0.61

POSITIVE LOGITS

the

1.26

 this

0.84

 both

0.84

be

0.74

0.72

 each

0.72

our

0.71

 these

0.71

an

0.70

any

0.70

Activations Density 0.349%

instances of timestamps or temporal markers

Preposition "to" followed by a word

to + number or unit of measure

No Comments

No Known Activations