INDEX

Explanations

clauses starting with "that"

oai_token-act-pair · gemini-2.0-flash

that

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.75

 kasarigan

-0.74

rungsseite

-0.63

 المعيارى

-0.63

 متعلقه

-0.63

verwijspagina

-0.58

webElementGuid

-0.57

TypedDataSet

-0.54

Bakgrunnsstoff

-0.53

 للاسماء

-0.53

POSITIVE LOGITS

’

0.60

JpaRepository

0.59

wende

0.52

deelte

0.49

Enumerated

0.48

 Vás

0.48

 idea

0.47

 createContext

0.47

aer

0.45

Activations Density 1.991%

clauses starting with "that"

that

No Comments

No Known Activations