INDEX

Explanations

instances of technical terminology or specialized concepts related to research methodology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

…

-1.07

…

-1.04

…”

-1.00

“

-1.00

“…”

-0.95

‘

-0.95

=’

-0.91

”…

-0.89

.’

-0.86

 præ

-0.86

POSITIVE LOGITS

parsedMessage

1.28

...."

1.12

 ....

1.07

 .....

1.05

NCS

1.04

'...

1.03

"....

1.03

 ...'

1.01

...'

1.00

 !...

1.00

Activations Density 0.096%

instances of technical terminology or specialized concepts related to research methodology

No Comments

No Known Activations