INDEX

Explanations

references to upcoming events or occurrences

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

But

-0.56

on

-0.55

Slf

-0.54

 Cataloging

-0.48

er

-0.47

-0.46

useEffect

-0.46

winston

-0.45

 neust

-0.45

POSITIVE LOGITS

 upcoming

2.88

upcoming

2.58

 Upcoming

2.45

 forthcoming

2.30

Upcoming

2.22

 impending

1.71

 kommende

1.68

 tomorrow

1.52

 futura

1.51

 future

1.49

Activations Density 0.036%

references to upcoming events or occurrences

No Comments

No Known Activations