INDEX

Explanations

sections and headings related to documents or reports

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

or

-0.59

but

-0.52

ing

-0.49

No

-0.49

ink

-0.49

and

-0.48

-0.43

lich

-0.43

so

-0.43

ish

-0.43

POSITIVE LOGITS

setVerticalGroup

1.06

RegistryLite

0.99

__":

0.89

ValueStyle

0.89

 ujednoznacz

0.86

 للاسماء

0.85

 مشين

0.85

 referenties

0.82

 дописавши

0.81

__':

0.79

Activations Density 0.290%

sections and headings related to documents or reports

No Comments

No Known Activations