INDEX

Explanations

elements and keywords related to health, medical conditions, and societal discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 فريبيس

-1.00

rungsseite

-0.87

GEBURTSDATUM

-0.85

 transfieras

-0.77

 للاسماء

-0.75

 Paglinawan

-0.74

SourceChecksum

-0.70

FieldBuilder

-0.68

\{\\

-0.65

 незавершена

-0.64

POSITIVE LOGITS

 although

1.26

 especially

1.05

 which

1.00

 including

0.99

although

0.94

 particularly

0.93

 though

0.93

 both

0.90

 vilket

0.88

 hvilket

0.85

Activations Density 1.152%

elements and keywords related to health, medical conditions, and societal discussions

No Comments

No Known Activations