INDEX

Explanations

indicators of the beginning of a new section or topic 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

ViewFeatures

-0.57



-0.51

 fiabilité

-0.50

 مرئيه

-0.50

 financières

-0.50

ToAction

-0.49

 gustaba

-0.48

 culturelles

-0.47

승

-0.46

 qualités

-0.45

POSITIVE LOGITS

Package

0.84

RegressionTest

0.80

 Package

0.78

 package

0.75

Notice

0.70

 note

0.69

esModule

0.68

ConstraintMaker

0.67

 Notice

0.66

typeorm

0.66

Activations Density 0.026%

indicators of the beginning of a new section or topic in the text

No Comments

No Known Activations