INDEX

Explanations

terms related to changes or trends in research metrics and outputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ecznie

-0.54

__*/

-0.52

 UITableViewCell

-0.51

orsese

-0.50

IContainer

-0.50

 numberWith

-0.49

 Lightboxes

-0.49

LookAnd

-0.47

.*")]

-0.47

hea

-0.45

POSITIVE LOGITS

 observed

0.78

 seen

0.77

 Seen

0.76

 noticed

0.70

 constaté

0.64

seen

0.63

 noted

0.63

 witnessed

0.63

observed

0.63

 pinulongan

0.61

Activations Density 0.594%

terms related to changes or trends in research metrics and outputs

No Comments

No Known Activations