INDEX

Explanations

references to specific areas or regions within a context

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

 phytoplankton

-0.77

 quoi

-0.73

lihood

-0.72

 Metallurgy

-0.71

 riga

-0.68

 iconTwitter

-0.67

 nevertheless

-0.67

udder

-0.66

Embeddable

-0.66

 Baptiste

-0.65

POSITIVE LOGITS

 area

2.41

 Area

2.21

area

2.20

 AREA

2.17

 areas

2.08

Area

2.06

AREA

2.02

 Areas

1.95

Areas

1.92

areas

1.91

Activations Density 0.096%

references to specific areas or regions within a context

No Comments

No Known Activations