INDEX

Explanations

assertions and emphasized statements, particularly those denoting importance or highlighting key points

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

Followed by "that"

np_acts-logits-general · gemini-2.0-flash

emphasized or noted facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__*/

-0.70

ContentLoaded

-0.69

 Administrativna

-0.68

Rüyada

-0.63

 <<<<<<<<<<<<<<

-0.63

⟬

-0.62

 estadounid

-0.61

rrggbb

-0.61

 мәкал

-0.58

 autorytatywna

-0.58

POSITIVE LOGITS

 interest

0.29

 Schmer

0.26

 principal

0.26

pe

0.26

rep

0.25

【

0.25

big

0.25

 squee

0.24

pat

0.24

 squash

0.24

Activations Density 2.356%

assertions and emphasized statements, particularly those denoting importance or highlighting key points

Followed by "that"

emphasized or noted facts

No Comments

No Known Activations