INDEX

Explanations

references to exhibitions and displays in a context related to art and technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

resultCode

-0.60

gettimeofday

-0.57

noch

-0.50

qrstuvwxyz

-0.49

 poliester

-0.48

ormais

-0.48

 NSCoder

-0.48

autogui

-0.48

abcdefghijklmnop

-0.48

 pengar

-0.48

POSITIVE LOGITS

 showcase

1.08

 showcasing

1.03

 showcases

1.01

showcase

0.96

 showcased

0.93

 exhibits

0.87

 Showcase

0.86

 exhibit

0.86

展示

0.85

 displays

0.84

Activations Density 0.240%

references to exhibitions and displays in a context related to art and technology

No Comments

No Known Activations