INDEX

Explanations

addresses or locations

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

street names and punctuation

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rien

-0.46

lucky

-0.43

Fer

-0.42

 jaune

-0.41

ziehen

-0.40

 môi

-0.40

moja

-0.40

 ihres

-0.40

 lucky

-0.40

 scheda

-0.39

POSITIVE LOGITS

LookAnd

1.03

Hozzáférés

0.98

parsedMessage

0.97

 pinulongan

0.91

 AssemblyCulture

0.89

 '\\;'

0.88

AndEndTag

0.87

AddTagHelper

0.87

клопе

0.84

 мәкал

0.83

Activations Density 0.003%

addresses or locations

street names and punctuation

No Comments

No Known Activations