INDEX

Explanations

references to personal lists or "bucket lists"

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

"list" or items in a list

np_acts-logits-general · gemini-2.0-flash

list and items on it

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

êques

-0.66

adpleegd

-0.64

 unknownFields

-0.61

IUrlHelper

-0.55

esez

-0.54

 achar

-0.54

 useParams

-0.52

yntaxException

-0.52

AddTagHelper

-0.51

 '\\;'

-0.49

POSITIVE LOGITS

 list

2.93

 lists

2.42

list

2.26

 List

2.23

 lista

2.17

 liste

2.15

 lijst

2.13

 LIST

2.12

 Liste

2.08

 Lists

2.01

Activations Density 0.369%

references to personal lists or "bucket lists"

"list" or items in a list

list and items on it

No Comments

No Known Activations