INDEX

Explanations

references to abstract concepts and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 hår

-0.74

 gills

-0.66

idUser

-0.64

 SAVINGS

-0.62

 resistenza

-0.61

ásban

-0.59

beiten

-0.59

веси

-0.59

 indietro

-0.59

 Belles

-0.59

POSITIVE LOGITS

 concepts

1.48

 concept

1.33

 Concepts

1.30

Concepts

1.27

 CONCEPT

1.26

Concept

1.20

 Concept

1.17

concepts

1.14

concept

1.12

 CONCEPTS

1.05

Activations Density 0.041%

references to abstract concepts and their relationships

No Comments

No Known Activations