INDEX

Explanations

legal terminology and arguments related to judicial proceedings

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

 محفوظة

-0.53

没事

-0.52

 Happen

-0.51

ModelMap

-0.51

 LoggerFactory

-0.51

matorium

-0.50

tesi

-0.48

BagConstraints

-0.48

éviter

-0.47

toHaveBeenCalled

-0.47

POSITIVE LOGITS

 fails

1.27

 lacks

1.10

 misses

1.09

 insufficient

1.07

 fail

1.06

 lacked

1.02

 inadequate

1.02

 inadequ

1.01

 failed

0.99

 Fails

0.98

Activations Density 0.870%

legal terminology and arguments related to judicial proceedings

No Comments

No Known Activations