INDEX

Explanations

patterns involving financial or legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

IFORN

-0.66

 contextLoads

-0.60

basicConfig

-0.58

Begriffsklä

-0.57

 Audiodateien

-0.53

ollectionView

-0.52

(&:

-0.52

 FormsModule

-0.51

verwijspagina

-0.51

Παραπομπές

-0.50

POSITIVE LOGITS

 warrant

0.65

 <<<<<<<<<<<<<<

0.62

 Warrant

0.62

LookAnd

0.57

 thermique

0.57

ruik

0.54

shutil

0.53

AndEndTag

0.53

warrant

0.52

ingga

0.52

Activations Density 0.679%

patterns involving financial or legal terminology

No Comments

No Known Activations

patterns involving financial or legal terminology

No Comments

No Known Activations