INDEX

Explanations

expressions of protest and declarations

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

Exclamations or emphasized words

np_acts-logits-general · gemini-2.0-flash

exclamations and declarations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.72

 €)

-0.72

RectangleBorder

-0.71

 bezeichneter

-0.71

didSet

-0.70

 старости

-0.70

发表于

-0.68

adays

-0.68

 Мексичка

-0.68

 createState

-0.67

POSITIVE LOGITS

0.67

!!!!

0.59

!!!

0.59

!"

0.58

!”

0.54

...

0.54

 yeah

0.53

 everybody

0.52

!!!!!

0.52

!!!!!!

0.50

Activations Density 0.186%

expressions of protest and declarations

Exclamations or emphasized words

exclamations and declarations

No Comments

No Known Activations