INDEX

Explanations

noun phrases that describe entities or organizations

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

 tartalomajánló

-0.73

OGND

-0.71

 Managua

-0.69

DoubleQuotes

-0.69

SharedCtor

-0.68

 MainAxisSize

-0.67

 liners

-0.67

 pinulongan

-0.67

Sucesor

-0.67

 swarovski

-0.66

POSITIVE LOGITS

basicConfig

0.59

]";

0.58

an

0.58

is

0.55

belongs

0.50

attente

0.49

0.48

An

0.48

 merupakan

0.47

Activations Density 0.357%

noun phrases that describe entities or organizations

No Comments

No Known Activations