INDEX

Explanations

phrases that express preference or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

ToBounds

-0.87

Vij

-0.71

 Williamson

-0.66

 uuidv

-0.66

 regla

-0.65

ActivityCompat

-0.65

labelledby

-0.64

Lue

-0.63

 Hermans

-0.63

зу

-0.62

POSITIVE LOGITS

uttosto

1.24

 Rather

1.06

rather

1.05

Rather

1.03

 rather

0.89

 ***/

0.88

 guère

0.82

 Bemer

0.82

 Fairly

0.81

 PLWABN

0.81

Activations Density 0.083%

phrases that express preference or comparison

No Comments

No Known Activations