INDEX

Explanations

geographical locations and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 surla

-0.88

out

-0.79

тності

-0.60

 Lebanese

-0.59

 Latvian

-0.59

JAMIN

-0.59

Out

-0.59

 Lithuanian

-0.58

 Armenian

-0.57

out

-0.57

POSITIVE LOGITS

land

0.71

 <>",

0.65

simpleType

0.63

 Countries

0.59

 lands

0.59

LAND

0.59

 land

0.59

աստ

0.59

 méri

0.58

 étoient

0.58

Activations Density 0.213%

geographical locations and associated entities

No Comments

No Known Activations