INDEX

Explanations

words that appear frequently in a document, often in a scattered way

oai_token-act-pair · gemini-2.0-flash

object attributes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ✭✭

-0.67

RetentionPolicy

-0.58

AutoScale

-0.58

EndContext

-0.57

 mergeFrom

-0.52

 betweenstory

-0.51

*}[

-0.49

 ProtoMessage

-0.49

tagHelperRunner

-0.48

 باخ

-0.47

POSITIVE LOGITS

twimg

0.68

 BoxDecoration

0.62

principalColumn

0.60

Unmarshaller

0.52

כשיו

0.52

setN

0.49

tisches

0.49

ToBounds

0.49

 gouver

0.47

atalyst

0.46

Activations Density 3.026%

words that appear frequently in a document, often in a scattered way

object attributes

No Comments

No Known Activations