INDEX

Explanations

occurrences of the word "used" and other related verbs describing actions or processes in a scientific or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

TagMode

-1.05

sizeCache

-0.99

rungsseite

-0.98

majánló

-0.98

 незавершена

-0.95

 increí

-0.94

 '\\;'

-0.93

 ſeinen

-0.93

 ویکی‌پدی

-0.92

 للاسماء

-0.92

POSITIVE LOGITS

↵↵

0.55

0.49

↵

0.43

<eos>

0.42

•

0.41

’

0.39

 Rosenberg

0.37

we

0.37

Activations Density 1.124%

occurrences of the word "used" and other related verbs describing actions or processes in a scientific or technical context

No Comments

No Known Activations