INDEX

Explanations

phrases related to fundamentalism and its critique

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

preceding negative or limiting terms

np_acts-logits-general · gemini-2.0-flash

exclusive, simplistic, reduction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 publiques

-0.56

 QWidget

-0.56

 humaines

-0.56

complexType

-0.55

 découver

-0.54

 foncé

-0.54

 AttributeSet

-0.54

 inconn

-0.52

 rempliss

-0.50

 couverts

-0.50

POSITIVE LOGITS

 reduction

0.75

 parochial

0.74

 redu

0.67

 simplistic

0.66

 Exclusive

0.64

 Reduction

0.64

 monolithic

0.64

 exclusive

0.63

Reduction

0.62

reduction

0.62

Activations Density 0.424%

phrases related to fundamentalism and its critique

preceding negative or limiting terms

exclusive, simplistic, reduction

No Comments

No Known Activations