INDEX

Explanations

markup or programming language elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 '\\;'

-0.76

jspb

-0.76



-0.73

✨:

-0.69

Welp

-0.68

 fût

-0.66

 فريبيس

-0.65

 betweenstory

-0.63

 TextInputType

-0.63

 nemlig

-0.63

POSITIVE LOGITS

0.64

Wherever

0.59

 people

0.59

 ourselves

0.58

 whatever

0.56

we

0.56

 lắm

0.55

We

0.54

 because

0.54

,”

0.54

Activations Density 0.051%

markup or programming language elements

No Comments

No Known Activations