INDEX

Explanations

phrases related to legal processes and disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

تقاوى

-0.91

 alſo

-0.90

BeginContext

-0.87

 ویکی‌پدیای

-0.87

 myſelf

-0.86

 purpoſe

-0.86

 pleaſure

-0.83

 neceff

-0.82

 Jefus

-0.82

 itſelf

-0.81

POSITIVE LOGITS

Pe

0.55

“

0.53

Re

0.53

Mo

0.51

omu

0.51

ளி

0.50

Se

0.49

Tri

0.49

parseLong

0.48

Activations Density 1.041%

phrases related to legal processes and disputes

No Comments

No Known Activations