INDEX

Explanations

names of people

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

usermodel

-0.67

 modelAndView

-0.60

 ویکی‌پدی

-0.56

SourceChecksum

-0.56

wayat

-0.55

contentLoaded

-0.54

bootstrapcdn

-0.54

pyplot

-0.54

Act

-0.53

 collectivités

-0.51

POSITIVE LOGITS

="{{$

0.65

 Maria

0.62

ificant

0.61

mari

0.57

TagHelper

0.57

 Jefus

0.57

terness

0.56

enação

0.56

 leaſt

0.56

islative

0.55

Activations Density 0.093%

names of people

No Comments

No Known Activations