INDEX

Explanations

markdown or structured code snippets, typically related to data formatting or HTML/XML tags

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

OPSIS

-0.60

GNA

-0.60

Sucesor

-0.59

StructEnd

-0.58

contentLoaded

-0.56

niająca

-0.55

orianCalendar

-0.54

codings

-0.54

onViewCreated

-0.53

createCanvas

-0.53

POSITIVE LOGITS

 item

2.43

 Item

2.21

Item

2.16

item

2.14

 ITEM

2.03

 items

2.00

ITEM

1.86

 Items

1.77

getItem

1.73

Items

1.67

Activations Density 0.067%

markdown or structured code snippets, typically related to data formatting or HTML/XML tags

No Comments

No Known Activations