INDEX

Explanations

legal terminology and concepts related to evidence and court proceedings

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

 disambiguazione

-0.70

 >=",

-0.67

 nakalista

-0.64

ορ

-0.58

 midwives

-0.58

 intptr

-0.57

Scénario

-0.56

trico

-0.56

 الحره

-0.55

]-'

-0.55

POSITIVE LOGITS

 itself

0.62

 kaynağından

0.54

 whome

0.53

 stesse

0.52

 whoever

0.47

 Whoever

0.46

 species

0.46

 yourself

0.46

 whatever

0.46

 gebied

0.46

Activations Density 1.631%

legal terminology and concepts related to evidence and court proceedings

No Comments

No Known Activations