INDEX

Explanations

phrases indicating high quality or superiority

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

iség

-0.69

Général

-0.68

rawdę

-0.67

}')

-0.63

 AssemblyCompany

-0.63

 circumstances

-0.63

 initWith

-0.62

Itinerary

-0.62

 gustó

-0.61

 deviceId

-0.61

POSITIVE LOGITS

TOP

2.24

top

2.21

Top

2.04

TOP

2.04

top

1.99

Top

1.96

 tops

1.93

 Tops

1.75

getTop

1.59

tops

1.57

Activations Density 0.065%

phrases indicating high quality or superiority

No Comments

No Known Activations