INDEX

Explanations

references to addresses and related identifying information

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

ızlık

-0.51

 paddy

-0.49

artement

-0.47

 Barns

-0.46

ầng

-0.45

 stere

-0.45

 progn

-0.45

ąp

-0.45

 Afonso

-0.44

Buses

-0.43

POSITIVE LOGITS

WebVitals

1.35

 nahilalakip

1.32

parsedMessage

1.23

 Normdatei

1.21

tvguidetime

1.11

MemoryWarning

1.08

ValueStyle

1.01

transQ

1.01

AndEndTag

1.00

 MessageBoxIcon

0.97

Activations Density 0.423%

references to addresses and related identifying information

No Comments

No Known Activations