INDEX

Explanations

the beginning of new text segments or sections

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

endphp

-0.73

 ModelExpression

-0.72

Rhestr

-0.72

DockStyle

-0.71

richTextPanel

-0.71

tagHelperRunner

-0.71

webElementXpaths

-0.71

WriteTagHelper

-0.70

 JpaRepository

-0.67

 lenker

-0.63

POSITIVE LOGITS

omenclature

0.66

 avoient

0.61

 Custody

0.60

pezif

0.59

ItemIndex

0.57

 Penit

0.57

 Maternity

0.57

 oscillatory

0.57

 étoient

0.56

 penit

0.56

Activations Density 0.536%

the beginning of new text segments or sections

No Comments

No Known Activations