INDEX

Explanations

code elements like comments, properties, and function definitions

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

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

ArrowToggle

-0.58

RunWith

-0.54

ItemBackground

-0.52

πουργ

-0.51

InitVars

-0.51

NamedQueries

-0.50

createClass

-0.47

 dál

-0.44

 réve

-0.43

laceae

-0.43

POSITIVE LOGITS

migrationBuilder

0.67

fillType

0.60

存于互联网档案馆

0.58

niająca

0.56

клопе

0.56

rowser

0.55

WriteAttribute

0.54

 Nacionales

0.54

getSupport

0.53

Према

0.53

Activations Density 0.090%

code elements like comments, properties, and function definitions

No Comments

No Known Activations