INDEX

Explanations

the presence of annotations or tags in the text

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

WriteBarrier

-0.68

RenderAtEndOf

-0.67

 Orrell

-0.56

 isolé

-0.56

UnusedPrivate

-0.55

FunctionFlags

-0.54

UrlResolution

-0.54

DoubleQuotes

-0.54

iko

-0.52

 ISOL

-0.50

POSITIVE LOGITS

author

0.81

 Савезне

0.73

 author

0.71

 Author

0.61

ClassName

0.58

parseFrom

0.55

 AssemblyProduct

0.55

ритори

0.54

featureID

0.53

Author

0.53

Activations Density 0.054%

the presence of annotations or tags in the text

No Comments

No Known Activations