INDEX

Explanations

significant quantities within code snippets, likely indicating important operations or constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

setVerticalGroup

-1.23

SourceChecksum

-1.19

Datuak

-1.10

 Савезне

-1.07

Personendaten

-1.07

featureID

-1.06

 AssemblyCompany

-1.02

 للاسماء

-1.01

richTextPanel

-1.01

Personensuche

-0.98

POSITIVE LOGITS

0.43

↵↵

0.43

0.41

ch

0.39

0.37

0.36

gud

0.36

 nahilalakip

0.34

Activations Density 2.328%

significant quantities within code snippets, likely indicating important operations or constructs

No Comments

No Known Activations