INDEX

Explanations

legal terms and concepts related to trials and judgments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ✭✭

-0.71

findpost

-0.69

PhysRevD

-0.68

MLLoader

-0.67

Portail

-0.63

OGND

-0.62

 كومونز

-0.62

hundred

-0.61

etches

-0.60

BeginContext

-0.60

POSITIVE LOGITS

ellar

0.65

perative

0.58

時的

0.57

 postoperative

0.54

########.

0.54

glichen

0.54

PreferredItem

0.53

 Afterwards

0.52

:+:

0.51

 afterwards

0.51

Activations Density 0.491%

legal terms and concepts related to trials and judgments

No Comments

No Known Activations