INDEX

Explanations

phrases indicating the concept of "within" different contexts or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

er

-0.75

TPS

-0.68

es

-0.64

cy

-0.64

io

-0.63

cps

-0.61

DSC

-0.61

 Gerber

-0.61

arth

-0.60

POSITIVE LOGITS

within

2.24

 Within

2.21

Within

2.18

 within

2.15

 WITHIN

2.07

 binnen

1.46

 innerhalb

1.44

 dentro

1.38

 entro

1.35

dentro

1.33

Activations Density 0.095%

phrases indicating the concept of "within" different contexts or situations

No Comments

No Known Activations