INDEX

Explanations

structured lists or organized elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Vidite

-0.79

Geplaatst

-0.75

enumi

-0.73

 الحره

-0.67

 Meksiku

-0.66

 ihop

-0.62

cidae

-0.60

ècie

-0.60

 réguli

-0.59

 CrossRef

-0.59

POSITIVE LOGITS

下载附件

0.55

timewa

0.55

évaluateur

0.53

']))

0.49

enegger

0.48

 <<<<<<<<<<<<<<

0.48

%")

0.47

))*

0.47

 ***!

0.47

']),

0.46

Activations Density 0.160%

structured lists or organized elements in the text

No Comments

No Known Activations