INDEX

Explanations

references to companies, organizations, or entities involved in significant actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

did

-0.49

Did

-0.48

 Will

-0.46

Did

-0.41

do

-0.41

do

-0.40

la

-0.40

ше

-0.40

Would

-0.39

Will

-0.39

POSITIVE LOGITS

 đang

1.22

 sedang

1.11

 estão

1.07

 estamos

1.06

กำลัง

1.04

 estou

1.03

 estás

0.99

 stanno

0.98

 está

0.97

SourceChecksum

0.97

Activations Density 0.526%

references to companies, organizations, or entities involved in significant actions or decisions

No Comments

No Known Activations