INDEX

Explanations

words and phrases common in academic papers describing research

oai_token-act-pair · gemini-2.0-flash

scientific research papers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-0.83

 myſelf

-0.72

 itſelf

-0.66

ſelf

-0.65

 Shakspeare

-0.63

 Majefty

-0.62

 Roskov

-0.62

 preſent

-0.60

ſelves

-0.60

 theſe

-0.60

POSITIVE LOGITS

CLAIMER

0.61

addGap

0.60

quium

0.59

arXiv

0.59

addContainerGap

0.59

 CreateTagHelper

0.58

 argue

0.57

脚注の使い方

0.56

 preprint

0.56

ínű

0.55

Activations Density 3.491%

words and phrases common in academic papers describing research

scientific research papers

No Comments

No Known Activations