INDEX

Explanations

trademarks and registered symbols associated with products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

cha

-0.63

 calendriers

-0.60

Bus

-0.60

bus

-0.59

tra

-0.58

 כת

-0.57

usto

-0.57

alen

-0.56

to

-0.56

 trouble

-0.56

POSITIVE LOGITS

 Cæsar

1.24

 Majefty

1.21

 itſelf

1.11

 purpoſe

1.09

circledR

1.06

 uſed

1.04

 Jefus

1.02

 themſelves

1.01

 himſelf

1.01

 Monfieur

1.00

Activations Density 0.180%

trademarks and registered symbols associated with products

No Comments

No Known Activations