INDEX

Explanations

references to immune response factors and signaling proteins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 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

RegressionTest

-0.58

InputBorder

-0.56

DataAnnotations

-0.48

 BUFFER

-0.47

 VERT

-0.45

 StringVar

-0.45

roman

-0.44

hassee

-0.43

 resourceCulture

-0.43

 Winaray

-0.43

POSITIVE LOGITS

IS

2.31

IS

1.73

ARE

1.35

WAS

1.17

CAN

1.13

HAS

1.10

 WILL

1.06

 DOES

1.01

DID

0.99

 WOULD

0.93

Activations Density 0.152%

references to immune response factors and signaling proteins

No Comments

No Known Activations