INDEX

Explanations

references to scientific concepts, figures, or examples within the text

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

Text within brackets (often references or citations)

np_acts-logits-general · gemini-2.0-flash

section references and learning materials

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Geplaatst

-0.69

 doInBackground

-0.64

awtextra

-0.64

 AssemblyCulture

-0.55

 betweenstory

-0.54

Carriera

-0.53

WithIOException

-0.52

JsonNode

-0.52

yntaxException

-0.51

contentLoaded

-0.51

POSITIVE LOGITS

本章

0.80

 Practice

0.75

Practice

0.75

 practice

0.73

practice

0.70

Learning

0.69

 introd

0.69

 leçon

0.66

learn

0.65

 Chapter

0.64

Activations Density 0.489%

references to scientific concepts, figures, or examples within the text

Text within brackets (often references or citations)

section references and learning materials

No Comments

No Known Activations