INDEX

Explanations

references to time periods and their significance or meaning

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

writerow

-0.57

 StringTokenizer

-0.51

Slf

-0.45

IVEREF

-0.45

awtextra

-0.41

MessageTagHelper

-0.41

labelledby

-0.40

ioutil

-0.36

יוון

-0.35

mathop

-0.35

POSITIVE LOGITS

Dentro

0.59

within

0.58

Within

0.55

 within

0.52

 Picchu

0.52

 Within

0.50

 innerhalb

0.50

 WITHIN

0.50

ToBounds

0.50

 intptr

0.47

Activations Density 0.152%

references to time periods and their significance or meaning

No Comments

No Known Activations

references to time periods and their significance or meaning

No Comments

No Known Activations