INDEX

Explanations

references to written content or posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 متعلقه

-0.60

 AssemblyTitle

-0.52

numerusform

-0.51

olin

-0.48

 cade

-0.47

 שוליים

-0.47

uders

-0.47

AttributeSet

-0.46

bree

-0.46

 report

-0.46

POSITIVE LOGITS

 emails

1.41

 posts

1.23

 Emails

1.22

emails

1.16

 Posts

1.16

 messages

1.09

 newsletters

1.05

 tweets

1.01

 letters

0.99

 articles

0.98

Activations Density 0.190%

references to written content or posts

No Comments

No Known Activations