INDEX

Explanations

phrases indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

geräte

-0.63

JsonHelper

-0.62

FLAGS

-0.59

bitField

-0.59

ględ

-0.57

getDescriptor

-0.56

BorderFactory

-0.56

expandindo

-0.55

ByExample

-0.55

HasColumnType

-0.54

POSITIVE LOGITS

 close

2.32

 Close

2.28

close

2.20

Close

2.19

 CLOSE

2.07

CLOSE

1.88

 closest

1.50

 closeness

1.46

 CLOS

1.45

 closer

1.45

Activations Density 0.126%

phrases indicating proximity or closeness

No Comments

No Known Activations