INDEX

Explanations

code documentation tags for summaries

oai_token-act-pair · gemini-2.0-flash

word patterns resembling technical documentation or code structure

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

Code snippets

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

Personendaten

-0.75

featureID

-0.70

Controllo

-0.66

তথ্যসূত্র

-0.63

 '\\;'

-0.62

'])){

-0.61

MessageTagHelper

-0.61

 Waray

-0.61

 touch

-0.60

optionalTypeArgs

-0.59

POSITIVE LOGITS

rungsseite

0.57

حياتها

0.55

opardi

0.52

Umb

0.49

angering

0.49

yntaxException

0.48

ỡng

0.47

 IConfiguration

0.46

ofag

0.46

VersionUID

0.46

Activations Density 0.557%

code documentation tags for summaries

word patterns resembling technical documentation or code structure

Code snippets

No Comments

No Known Activations