INDEX

Explanations

phrases that indicate frequency or commonality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ilstein

-0.51

entitled

-0.50

 enorme

-0.50

enumi

-0.50

 calendriers

-0.49

 enormous

-0.49

 Penh

-0.49

 verte

-0.48

łucha

-0.48

 dint

-0.47

POSITIVE LOGITS

 commonly

2.72

 Commonly

2.44

 typically

2.36

commonly

2.29

 usually

2.23

 often

2.21

 frequently

2.20

typically

2.14

 Typically

2.09

usually

2.07

Activations Density 0.111%

phrases that indicate frequency or commonality

No Comments

No Known Activations