INDEX

Explanations

indicators of new beginnings or significant transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 चीज़ों

-0.55

alyptus

-0.52

 समीक्षाएं

-0.51

 насељу

-0.48

MONG

-0.47

ceğiniz

-0.46

EXCHANGE

-0.46

alibaba

-0.46

zsche

-0.45

 gawas

-0.45

POSITIVE LOGITS

ClientSize

0.63

tagext

0.59

 Waray

0.58

Geplaatst

0.57

تقاوى

0.57

 autorytatywna

0.55

Koordinaten

0.54

 coûte

0.53

 IActionResult

0.53

 Roskov

0.53

Activations Density 0.026%

indicators of new beginnings or significant transitions

No Comments

No Known Activations