INDEX

Explanations

numerical data and codes related to scientific or technical content.

oai_token-act-pair · gpt-4o-mini Triggered by @bot

technical data related to computer programming.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

HTML markup and structure, particularly focusing on table elements and their attributes.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Tokens preceded by null characters or unusual symbols

np_acts-logits-general · gemini-2.0-flash

compound words or specific abbreviations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 noten

-0.54

 HomeController

-0.53

izade

-0.49

pell

-0.48

Rhestr

-0.47

veloper

-0.46

idence

-0.45

 članak

-0.45

 devin

-0.45

 Impression

-0.45

POSITIVE LOGITS

ngdoc

0.65

rxjs

0.62

CDCl

0.61

 calorías

0.59

asgi

0.58

DataSetChanged

0.57

"](

0.57

'],'

0.57

"]),

0.56

']],

0.56

Activations Density 0.059%

numerical data and codes related to scientific or technical content.

technical data related to computer programming.

HTML markup and structure, particularly focusing on table elements and their attributes.

Tokens preceded by null characters or unusual symbols

compound words or specific abbreviations

No Comments

No Known Activations