INDEX

Explanations

statements indicating existence or the presence of concepts

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

Follows existential quantifiers (there is/are)

np_acts-logits-general · gemini-2.0-flash

"there is" and negations

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

mentions

-0.49

 featured

-0.48

maier

-0.47

ionales

-0.45

IndentedString

-0.43

DeleteBehavior

-0.43

 declarat

-0.42

かで

-0.42

 déclarations

-0.42

iligung

-0.42

POSITIVE LOGITS

ChildScrollView

0.83

 esistono

0.77

RectangleBorder

0.73

 reaſon

0.70

rungsseite

0.69

digm

0.67

 beſt

0.65

 Majefty

0.64

 ways

0.63

 exceptions

0.62

Activations Density 0.162%

statements indicating existence or the presence of concepts

Follows existential quantifiers (there is/are)

"there is" and negations

No Comments

No Known Activations