INDEX

Explanations

questions that require clarification or validation

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

Билгалдахарш

-0.79

Espèce

-0.72

 ligiloj

-0.69

 myſelf

-0.68

Dış

-0.67

Geplaatst

-0.65

Према

-0.65

 photolibrary

-0.62

Hyg

-0.62



-0.62

POSITIVE LOGITS

ok

1.38

 understood

1.33

 okay

1.32

OK

1.31

Understood

1.26

 Okay

1.20

Ok

1.18

Gotcha

1.17

Ok

1.16

OK

1.15

Activations Density 0.152%

questions that require clarification or validation

No Comments

No Known Activations