INDEX

Explanations

elements related to scientific diagrams and figures

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

Numbers within parentheses

np_acts-logits-general · gemini-2.0-flash

image captions with identifiers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.57

reportWebVitals

-0.51

flashdata

-0.51

теристика

-0.51

hasMoreElements

-0.50

all

-0.49

/******/

-0.48

Kariera

-0.47

<>

-0.47

人都

-0.46

POSITIVE LOGITS

 resized

0.69

ussian

0.65

 cropping

0.64

 Lordship

0.63

 enlarged

0.62

 consultato

0.62

 cropped

0.62

 miniatur

0.61

png

0.61

 Púb

0.61

Activations Density 0.519%

elements related to scientific diagrams and figures

Numbers within parentheses

image captions with identifiers

No Comments

No Known Activations