INDEX

Explanations

phrases related to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 &___

-0.53

 defaultstate

-0.50

setVerticalGroup

-0.50

 contextLoads

-0.49

errHandler

-0.47

 AssemblyTitle

-0.46

findpost

-0.45

 getItemCount

-0.45

 transfieras

-0.44

zystać

-0.42

POSITIVE LOGITS

 earned

1.16

 earn

1.09

 earning

1.06

 earns

1.01

Earn

0.92

earned

0.90

 clinched

0.88

 bagged

0.87

 secured

0.85

earn

0.85

Activations Density 0.261%

phrases related to awards and recognitions

No Comments

No Known Activations