INDEX

Explanations

phrases indicating collaboration or connection between thoughts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

iglio

-0.51

illon

-0.51

 Reuter

-0.49

 Nowak

-0.46

sp

-0.46

سانی

-0.46

 venter

-0.45

ейс

-0.45

isier

-0.44

EnableWeb

-0.44

POSITIVE LOGITS

how

2.64

how

2.00

 what

1.95

 cómo

1.74

why

1.73

what

1.70

 bagaimana

1.58

How

1.57

How

1.50

why

1.48

Activations Density 0.307%

phrases indicating collaboration or connection between thoughts or ideas

No Comments

No Known Activations

phrases indicating collaboration or connection between thoughts or ideas

No Comments

No Known Activations