INDEX

Explanations

words related to legal terms and their applicability in different contexts

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

referring to specific instances

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

TagMode

-0.38

çe

-0.37

berdayakan

-0.32

 QtCore

-0.31

 croire

-0.29

 Mittelalter

-0.29

tagHelperRunner

-0.28

 Inspection

-0.28

 Elevation

-0.28

 tourisme

-0.28

POSITIVE LOGITS

OGND

0.62

Tembelea

0.59

 respective

0.58

 "..\..\..\

0.56

各自

0.55

RTGC

0.53

RTSN

0.53

Cubit

0.52

+#+#

0.51

RTLD

0.51

Activations Density 0.109%

words related to legal terms and their applicability in different contexts

referring to specific instances

No Comments

No Known Activations