INDEX

Explanations

phrases related to reading or viewing additional content

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

"Read more" marker

np_acts-logits-general · gemini-2.0-flash

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

tanleria

-0.77

Cyfeiriadau

-0.73

 resourceCulture

-0.65

InSection

-0.62

 دیکھیے

-0.59

 namelijk

-0.58

 calendriers

-0.58

RepeatedField

-0.56

 jScrollPane

-0.56

بوابة

-0.56

POSITIVE LOGITS

 more

0.70

setArguments

0.58

 More

0.57

 περισσότε

0.56

 figliu

0.51

më

0.51

olites

0.51

atiz

0.50

oczes

0.49

Citiți

0.49

Activations Density 0.057%

phrases related to reading or viewing additional content

"Read more" marker

Read more

No Comments

No Known Activations