INDEX

Explanations

book citation information including publisher and city

oai_token-act-pair · gemini-2.0-flash

references to academic publishers and locations

np_token-act-pair-logits · gpt-4o-mini

city names

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

NameInMap

-0.79

Spoljašnje

-0.66

 betweenstory

-0.62

 chi̍t

-0.61

ValueStyle

-0.61

########.

-0.60

UnusedPrivate

-0.59

 Infórmanos

-0.59

oa̍t

-0.58

UserScript

-0.57

POSITIVE LOGITS

 للمعارف

0.47

CopyWith

0.47

newArrayList

0.47

katkan

0.46

ChildScrollView

0.46

iyor

0.45

 JpaRepository

0.44

نس

0.44

oredCriteria

0.43

EClass

0.42

Activations Density 1.259%

book citation information including publisher and city

references to academic publishers and locations

city names

No Comments

No Known Activations