INDEX

Explanations

words and phrases used in lists and comparisons

oai_token-act-pair · gemini-2.0-flash

steps/traits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.64

 kasarigan

-0.59

penup

-0.57

IntoConstraints

-0.57

ագրություններ

-0.51

COMMERCIAL

-0.49

 Trail

-0.48

 FetchType

-0.48

 burs

-0.48

án

-0.47

POSITIVE LOGITS

+#+#

0.97

 Paglinawan

0.81

MessageOf

0.65

 varandra

0.63

 näytte

0.60

 дописавши

0.58

setVerticalGroup

0.54

 répondu

0.52

Hochspringen

0.52

 meille

0.52

Activations Density 1.241%

words and phrases used in lists and comparisons

steps/traits

No Comments

No Known Activations