INDEX

Explanations

nested structures or complex object definitions in code

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

ors

-0.66

—

-0.60

vertx

-0.53

lyd

-0.53

he

-0.51

He

-0.51

umlu

-0.50

לה

-0.49

IDATE

-0.49

POSITIVE LOGITS

OGND

1.01

 autorytatywna

0.88

出版年

0.83

 reaſon

0.81

!!</

0.81

 neceffary

0.80

 myſelf

0.78

 raiſ

0.77

 cref

0.77

 Sinh

0.77

Activations Density 0.051%

nested structures or complex object definitions in code

No Comments

No Known Activations