INDEX

Explanations

symbols or characters used in programming or markup languages

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

Quoted text with ">" at the beginning

np_acts-logits-general · gemini-2.0-flash

greater than symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

istic

-0.61

ation

-0.57

-0.55

scriptcase

-0.55

son

-0.55

providedIn

-0.51

istani

-0.50

PreferredItem

-0.49

 localObject

-0.48

 AdapterView

-0.48

POSITIVE LOGITS

>>>>>>>>

1.26

>>>>>>

1.16

>>>>

1.15

>>>>>>>

1.13

.>

1.00

>>>>>

1.00

>>>

0.99

_>

0.99

_<

0.99

Activations Density 0.207%

symbols or characters used in programming or markup languages

Quoted text with ">" at the beginning

greater than symbol

No Comments

No Known Activations