INDEX

Explanations

sequences or structures indicative of programming syntax or expressions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-1.16

PreferredItem

-1.15

хьтан

-1.07

+#+#

-1.00

DOCTYPE

-0.96

principalColumn

-0.96

 SafeMath

-0.96

Vidite

-0.95

 GenerationType

-0.94

 Paglinawan

-0.94

POSITIVE LOGITS

“

0.48

0.47

</strong>

0.46

‘

0.46

↵

0.45

（

0.45

↵↵

0.43

The

0.43

（

0.41

his

0.41

Activations Density 0.624%

sequences or structures indicative of programming syntax or expressions

No Comments

No Known Activations