INDEX

Explanations

references to the Olympics

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

Eure

-0.51

 kahve

-0.50

PerformLayout

-0.49

oa̍t

-0.48

 Navarre

-0.48

issau

-0.47

apunov

-0.47

onActivityResult

-0.45

 Cytometry

-0.45

 weevil

-0.45

POSITIVE LOGITS

 Olympics

1.40

 Olympic

1.33

 Games

1.12

Olympic

1.07

 olymp

1.03

 Olymp

1.01

 olympic

0.98

Olymp

0.97

 olimp

0.96

 games

0.92

Activations Density 0.078%

references to the Olympics

No Comments

No Known Activations