INDEX

Explanations

references to external or outside entities and information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

gatsby

-0.64

 EconPapers

-0.64

formik

-0.62

harusnya

-0.56

 Umsatz

-0.56

 Waray

-0.55

#+#

-0.55

 disponibilités

-0.54

raborty

-0.53

ﬃ

-0.53

POSITIVE LOGITS

 outside

3.83

 Outside

3.62

outside

3.61

Outside

3.58

 OUTSIDE

3.30

OUTSIDE

3.03

 utanför

2.37

 buiten

2.24

extérieur

2.20

 exterior

2.13

Activations Density 0.075%

references to external or outside entities and information

No Comments

No Known Activations

references to external or outside entities and information

No Comments

No Known Activations