INDEX

Explanations

references to individual entities and specific types of organizations or systems

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

-0.45

he

-0.45

-0.44

-0.41

 eget

-0.40

衛門

-0.40

 tutt

-0.40

 three

-0.40

 four

-0.39

at

-0.39

POSITIVE LOGITS

 fubject

1.03

 itſelf

1.02

 Majefty

1.01

ſelves

1.01

ſelf

1.00

 Chriftian

0.95

 perſon

0.95

 houſe

0.94

 myſelf

0.94

 particular

0.93

Activations Density 0.441%

references to individual entities and specific types of organizations or systems

No Comments

No Known Activations