INDEX

Explanations

concepts related to evidence and arguments in legal contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ides

-0.46

rollup

-0.46

IDES

-0.45

Sub

-0.44

lides

-0.44

air

-0.44

Sub

-0.44

tym

-0.42

.”

-0.41

“

-0.41

POSITIVE LOGITS

 nahilalakip

0.99

 Biôgrafia

0.95

OGND

0.93

NameInMap

0.90

Tikang

0.90

WebVitals

0.90

 ModelExpression

0.89

complexContent

0.87

Diweddarwch

0.84

ыгана

0.83

Activations Density 0.352%

concepts related to evidence and arguments in legal contexts

No Comments

No Known Activations