INDEX

Explanations

programming-related keywords or syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 rowspan

-0.66

InitVars

-0.65

hoeddwyd

-0.63

 transfieras

-0.60

 estekak

-0.60

 Chwiliwch

-0.60

 мәкал

-0.59

 виправивши

-0.59

AsUp

-0.59

 tartalomajánló

-0.57

POSITIVE LOGITS

 WebDriverWait

0.53

dostęp

0.50

 envol

0.49

astify

0.49

BASEPATH

0.47

 attendu

0.46

AddHtmlAttribute

0.45

zubauen

0.45

gj

0.44

 leggen

0.44

Activations Density 0.131%

programming-related keywords or syntax

No Comments

No Known Activations