INDEX

Explanations

mathematical expressions and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 talvez

-0.56

istoitu

-0.56

 maybe

-0.50

Esperamos

-0.47

むしろ

-0.47

Hopefully

-0.46

Прият

-0.45

maybe

-0.45

 cref

-0.45

Geplaatst

-0.44

POSITIVE LOGITS

 describe

1.06

 Describe

1.02

 calculate

1.02

 write

1.02

 explain

1.01

 Explain

1.00

 what

0.96

Describe

0.95

Write

0.95

 Write

0.93

Activations Density 1.636%

mathematical expressions and calculations

No Comments

No Known Activations