INDEX

Explanations

references to proximity and closeness

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

sprogramm

-0.61

yntax

-0.55

Abp

-0.54

漿

-0.53

PHeader

-0.53

IsMutable

-0.51

XMLSchema

-0.51

TypedDataSet

-0.51

abestanden

-0.50

 Kompon

-0.50

POSITIVE LOGITS

 proximity

1.21

 close

1.02

 Close

1.01

 CLOSE

0.99

 Proximity

0.94

Close

0.94

CLOSE

0.90

close

0.85

 closer

0.83

 Closer

0.83

Activations Density 0.081%

references to proximity and closeness

No Comments

No Known Activations