INDEX

Explanations

hierarchical structures or formats in data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

au

-0.50

 Chris

-0.50

зю

-0.50

 First

-0.48

San

-0.48

nisk

-0.46

 present

-0.46

ellee

-0.46

AsUp

-0.46

if

-0.45

POSITIVE LOGITS

 وتسجيلات

0.88

ValueStyle

0.85

 itſelf

0.84

 ་་

0.81

AddTagHelper

0.79

mybatisplus

0.78

+#+

0.78

ectady

0.76

OGND

0.75

 myſelf

0.75

Activations Density 0.135%

hierarchical structures or formats in data

No Comments

No Known Activations