INDEX

Explanations

technical or programming-related terms and concepts, particularly those associated with image processing or transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

CGContext

-0.51

 FormGroup

-0.48

 Bond

-0.47

fabs

-0.47

effectively

-0.45

cshtml

-0.44

ButtonModule

-0.43

effec

-0.42

 belts

-0.41

API

-0.41

POSITIVE LOGITS

 <>",

0.68

хьтан

0.68

 kasarigan

0.66

 مشين

0.65

...

0.63

{[

0.61

 celulares

0.60

char

0.60

hartt

0.59

rawDesc

0.59

Activations Density 0.092%

technical or programming-related terms and concepts, particularly those associated with image processing or transformations

No Comments

No Known Activations