INDEX

Explanations

references to pharmaceutical companies and their products or trials

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 auffi

-0.61

enumi

-0.57

 CHAPITRE

-0.57

 Estad

-0.56

 Undang

-0.56

 Chapitre

-0.55

moiselle

-0.55

rrggbb

-0.54

 ainfi

-0.54

modium

-0.54

POSITIVE LOGITS

 Holdings

0.67

 فريبيس

0.66

AddHtmlAttribute

0.62

Inc

0.61

UseVisualStyle

0.61

Ltd

0.60

 HOLD

0.59

 Holding

0.58

LLC

0.57

 Group

0.57

Activations Density 0.347%

references to pharmaceutical companies and their products or trials

No Comments

No Known Activations