INDEX

Explanations

keywords and phrases related to formal documents, legal terms, and administrative processes

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

+#+

-0.53

soort

-0.50

 okuyayım

-0.49

μως

-0.49

GOTREF

-0.48

verwijspagina

-0.47

 متعلقه

-0.47

adpleegd

-0.47

nière

-0.46

 Commencez

-0.46

POSITIVE LOGITS

setVerticalGroup

0.69

jsonwebtoken

0.58

ImageContext

0.58

 useSelector

0.57

<bos>

0.57

 cavalry

0.56

PutMapping

0.56

.$.

0.54

 FetchType

0.54

vartis

0.54

Activations Density 3.214%

keywords and phrases related to formal documents, legal terms, and administrative processes

No Comments

No Known Activations