INDEX

Explanations

mathematical expressions and formal definitions related to energy and density functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

"</

-0.68

+'</

-0.65

/'.$

-0.64

_'.$

-0.60

ˈ

-0.59

".

-0.59

.)}

-0.59

/'+

-0.58

?!”

-0.58

StoryboardSegue

-0.58

POSITIVE LOGITS

\[

0.86

↵↵

0.85

0.78

ViewFeatures

0.74

 suivante

0.66

↵↵↵

0.64

$$

0.62

 AssemblyCulture

0.58

setVerticalGroup

0.57

DockStyle

0.53

Activations Density 1.343%

mathematical expressions and formal definitions related to energy and density functions

No Comments

No Known Activations