INDEX

Explanations

references to totality or individuality, often phrased as "every single" or "each and every."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

two

-0.55

XmlType

-0.51

 Sicilia

-0.49

Identifiers

-0.48

 thiệu

-0.47

bbean

-0.46

arjo

-0.45

dequeue

-0.45

Geograf

-0.45

Osob

-0.45

POSITIVE LOGITS

everything

1.24

 everything

1.18

Everything

1.17

 every

1.16

 Everything

1.16

EVERY

1.16

 EVERYTHING

1.14

every

1.13

 EVERY

1.07

Every

1.04

Activations Density 0.139%

references to totality or individuality, often phrased as "every single" or "each and every."

No Comments

No Known Activations