INDEX

Explanations

references to location or context markers related to "around"

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

"around"

np_acts-logits-general · gemini-2.0-flash

around

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

<bos>

-0.41

 незавершена

-0.40

 tjen

-0.37

-0.36

enskap

-0.32

vény

-0.31

 Dutton

-0.30

 moglie

-0.29

bison

-0.29

ítě

-0.28

POSITIVE LOGITS

around

2.20

Around

2.20

 around

2.20

 AROUND

2.14

 Around

2.14

AROUND

1.94

 autour

1.63

 alrededor

1.59

 вокруг

1.55

 intorno

1.49

Activations Density 0.090%

references to location or context markers related to "around"

"around"

around

No Comments

No Known Activations

references to location or context markers related to "around"

"around"

around

No Comments

No Known Activations