INDEX

Explanations

references related to the word "Can" or variations of "Can" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Попис

-0.57

Diwedd

-0.54

bootstrapcdn

-0.54

 Administrativna

-0.53

mischer

-0.53

omeness

-0.51

Demografia

-0.49

usermodel

-0.49

εια

-0.49

libft

-0.48

POSITIVE LOGITS

 Cans

0.65

ParallelGroup

0.64

 Spyder

0.60

CAN

0.58

CAN

0.58

 cans

0.57

Sino

0.56

cans

0.55

 Scro

0.55

 كومونز

0.54

Activations Density 0.109%

references related to the word "Can" or variations of "Can" in different contexts

No Comments

No Known Activations